paper.bib

@incollection{Connor2017,
author = {Connor, Richard and Vadicamo, Lucia and Rabitti, Fausto},
title = {{High-Dimensional Simplexes for Supermetric Search}},
booktitle = {Similarity Search and Applications},
year = {2017},
pages = {96--109},
publisher = {Springer},
}

@incollection{Connor2016,
author = {Connor, Richard},
title = {{A Tale of Four Metrics}},
booktitle = {Similarity Search and Applications},
year = {2016},
editor = {Amsaleg, Laurent and Houle, Michael E and Schubert, Erich},
pages = {210--217},
publisher = {Springer},
}

@article{Yujian2007,
author = {L. Bo and L. Yujian},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
title = {A Normalized {L}evenshtein Distance Metric},
year = {2007},
volume = {29},
number = {},
pages = {1091-1095},
keywords={Sequence comparison; Levenshtein distance; normalized edit distance; metric; AESA.},
doi = {10.1109/TPAMI.2007.1078},
ISSN = {0162-8828},
}
%%url = {doi.ieeecomputersociety.org/10.1109/TPAMI.2007.1078},

@inproceedings{Broder1997,
 author = {Broder, A.},
 title = {On the Resemblance and Containment of Documents},
 booktitle = {IEEE Compression and Complexity of Sequences},
 year = {1997},
 isbn = {0-8186-8132-2},
 pages = {21--29},
 acmid = {830043},
 address = {Salerno, Italy},
}
 
@misc{Dibben2012,
 author = {Dibben, C. and Williamson, L. and Huang, Z.},
 title = {Digitising {S}cotland},
 year = {2012},
 url = {http://gtr.rcuk.ac.uk/projects?ref=ES/K00574X/2},
 publisher = {Economic and Social  Research Council},
}

@misc{Cora2017,
 author = {McCallum, A.},
 title = {Cora Dataset: cora.csv},
 year = {2017},
 url = {https://doi.org/10.3886/E4728V1},
 publisher = {Inter-university Consortium for Political and Social Research [distributor]},
}

@ARTICLE{Levenshtein66,
	author = {V Levenshtein},
	title = {Binary codes capable of correcting deletions, insertions and reversals},
	journal = {Cybernetics and Control Theory},
	year = {1966},
	number = {10},
	pages = {707--710}
}

@article{Li2006,
 author = {Li, Chen and Jin, Liang and Mehrotra, Sharad},
 title = {Supporting Efficient Record Linkage for Large Data Sets Using Mapping Techniques},
 journal = {World Wide Web},
 issue_date = {December  2006},
 volume = {9},
 number = {4},
 _month = dec,
 year = {2006},
 issn = {1386-145X},
 pages = {557--584},
 numpages = {28},
 acmid = {1210411},
 publisher = {Kluwer Academic Publishers},
 address = {Hingham, MA, USA},
 keywords = {data cleaning, record linkage, similarity search, stringMap},
} 

@article{Hjaltason1998,
 author = {Hjaltason, G\'{\i}sli R. and Samet, Hanan},
 title = {Incremental Distance Join Algorithms for Spatial Databases},
 journal = {SIGMOD Rec.},
 issue_date = {June 1998},
 volume = {27},
 number = {2},
 year = {1998},
 issn = {0163-5808},
 pages = {237--248},
 numpages = {12},
 acmid = {276326},
 publisher = {ACM},
 address = {New York, NY, USA},
} 

@book{Zezula2010,
 author = {Zezula, Pavel and Amato, Giuseppe and Dohnal, Vlastislav and Batko, Michal},
 title = {Similarity Search: The Metric Space Approach},
 year = {2010},
 isbn = {1441939725, 9781441939722},
 _edition = {1st},
 publisher = {Springer},
} 

@INPROCEEDINGS{Ciaccia97indexingmetric,
    author = {P. Ciaccia and M. Patella and F. Rabitti and P. Zezula},
    title = {Indexing Metric Spaces with {M}-tree},
    booktitle = {Italian Symposium on Advanced Database Systems},
    year = {1997},
    pages = {67--86},
    volume = {97}
}

@Article{Yu2016,
author="Yu, Minghe
and Li, Guoliang
and Deng, Dong
and Feng, Jianhua",
title="String similarity search and join: a survey",
journal="Frontiers of Computer Science",
year="2016",
month="Jun",
day="01",
volume="10",
number="3",
pages="399--417",
abstract="String similarity search and join are two important operations in data cleaning and integration, which extend traditional exact search and exact join operations in databases by tolerating the errors and inconsistencies in the data. They have many real-world applications, such as spell checking, duplicate detection, entity resolution, and webpage clustering. Although these two problems have been extensively studied in the recent decade, there is no thorough survey. In this paper, we present a comprehensive survey on string similarity search and join. We first give the problem definitions and introduce widely-used similarity functions to quantify the similarity. We then present an extensive set of algorithms for string similarity search and join. We also discuss their variants, including approximate entity extraction, type-ahead search, and approximate substring matching. Finally, we provide some open datasets and summarize some research challenges and open problems.",
issn="2095-2236",
doi="10.1007/s11704-015-5900-5",
_url="https://doi.org/10.1007/s11704-015-5900-5"
}

@inproceedings{Steorts2014,
  title={A comparison of blocking methods for record linkage},
  author={Steorts, Rebecca C and Ventura, Samuel L and Sadinle, Mauricio and Fienberg, Stephen E},
  booktitle={PSD},
  pages={253--268},
  year={2014},
  organization={Springer},
  address = {Eivissa, Spain},
}

@article{amato2014mi,
  title={MI-File: using inverted files for scalable approximate similarity search},
  author={Amato, Giuseppe and Gennaro, Claudio and Savino, Pasquale},
  journal={Multimedia tools and applications},
  volume={71},
  number={3},
  pages={1333--1362},
  year={2014},
  publisher={Springer}
}

@inproceedings{paolociaccia2m,
  author =    {Paolo Ciaccia and Marco Patella and Pavel Zezula},
  title =     {M-tree: An Efficient Access Method for Similarity Search in Metric Spaces},
  booktitle = {23rd VLDB Conference},
  address =   {Athens, Greece},
  pages =     {426--435},
  year =      1997
}

@article{reid2002,
  title={Nineteenth-century {Scottish} demography from linked
  censuses and civil registers: A `sets of related individuals'
  approach},
  author={Reid, Alice and Davies, Ros and Garrett, Eilidh},
  journal={History and Computing},
  volume={14},
  number={1-2},
  pages={61--86},
  year={2002},
  publisher={Edinburgh University Press}
}

@article{reid2006,
  title={Scottish Census Enumerators' Books: {Skye}, {Kilmarnock},
  {Rothiemay} and {Torthorwald}, 1861--1901},
  author={Reid, A and Garrett, E and Davies, R and Blaikie, A},
  journal={Economic and Social Data Service},
  year={2006}
}

ro@techreport{ABS05,
  author =      {Lewis Conn and Glenys Bishop},
  title =       {Exploring Methods for Creating a Longitudinal Census
                 Dataset},
  institution = {Australian Bureau of Statistics},
  address =     {Canberra},
  number =      {1352.0.55.076},
  year =        2005
}

@inproceedings{Adl09,
  author =    {Noha Adly},
  title =     {Efficient Record Linkage using a Double Embedding
               Scheme},
  booktitle = {DMIN},
  pages =     {274--281},
  address =   {Las Vegas},
  year =      2009
}

@inproceedings{Agg00,
  author =    {Charu C. Aggarwal and Philip S. Yu},
  title =     {The {IGrid} index: Reversing the Dimensionality Curse
               for Similarity Indexing in High Dimensional Space},
  booktitle = {ACM SIGKDD},
  address =   {Boston},
  pages =     {119--129},
  year =      2000
}

@book{Agg08,
  title =     {Privacy-preserving data mining: models and algorithms},
  author =    {Charu C. Aggarwal and Philip S. Yu},
  publisher = {Springer},
  series =    {Advances in Database Systems},
  volume =    34,
  year =      2008
}

@book{Agg09,
  author =    {Charu C. Aggarwal},
  title =     {Managing and Mining Uncertain Data},
  series =    {Advances in Database Systems},
  publisher = {Springer},
  volume =    35,
  year =      2009
}

@inproceedings{Agi04,
  title =     {Mining reference tables for automatic text
               segmentation},
  author =    {Agichtein, E. and Ganti, V.},
  booktitle = {ACM SIGKDD},
  address =   {Seattle},
  pages =     {20--29},
  year =      2004
}

@inproceedings{Agr03,
  title =     {Information sharing across private databases},
  author =    {Agrawal, R. and Evfimievski, A. and Srikant, R.},
  booktitle = {ACM SIGMOD},
  address =   {San Diego},
  pages =     {86--97},
  year =      2003
}

@inproceedings{Aiz05,
  author =    {Akiko Aizawa and Keizo Oyama},
  title =     {A fast Linkage Detection Scheme for Multi-Source
               Information Integration},
  booktitle = {WIRI},
  address =   {Tokyo},
  pages =     {30--39},
  year =      2005
}

@inproceedings{All05,
  title =     {Blocking-aware private record linkage},
  author =    {Ali Al-Lawati and Dongwon Lee and Patrick McDaniel},
  booktitle = {International Workshop on Information Quality in
               Information Systems},
  address =   {Baltimore},
  pages =     {59--68},
  year =      2005
}

@inproceedings{Alv09,
  title =        {Interstate voter registration database matching: the
                  {Oregon-Washington} 2008 pilot project},
  author =       {Alvarez, R.M. and Jonas, J. and Winkler, W.E. and
                  Wright, R.N.},
  booktitle =    {Workshop on Trustworthy Elections},
  organization = {USENIX Association},
  pages =        {17--17},
  year =         2009
}

@article{And08,
  author =  {Anderson, K.B. and Durbin, E. and Salinger, M.A.},
  title =   {Identity theft},
  journal = {The Journal of Economic Perspectives},
  volume =  22,
  number =  2,
  pages =   {171--192},
  year =    2008
}

@article{Ant14a,
  title =     {Tracking people over time in 19th century {Canada} for
               longitudinal analysis},
  author =    {Luiza Antonie and Kris Inwood and Daniel J. Lizotte and
               J. Andrew Ross},
  journal =   {Machine Learning},
  publisher = {Springer},
  volume =    95,
  pages =     {129--146},
  year =      2014
}

@InProceedings{Ant14b,
  author =    {Antonie, Luiza and Inwood, Kris and Ross, Andrew},
  title =     {Dancing with dirty data: Problems in the extraction
               of life-course evidence from historical censuses},
  booktitle = {Population Reconstruction},
  Taddress =  {Amsterdam},
  year =      2014
}

@inproceedings{Ara09,
  title =     {A grammar-based entity representation framework for
               data cleaning},
  author =    {Arasu, Arvind and Kaushik, Raghav},
  booktitle = {ACM SIGMOD},
  address =   {Providence, Rhode Island},
  pages =     {233--244},
  year =      2009
}

@inproceedings{Ara10,
  title =     {On active learning of record matching packages},
  author =    {Arasu, Arvind and G{\"o}tz, Michaela and Kaushik,
               Raghav},
  booktitle = {ACM SIGMOD},
  address =   {Indianapolis},
  pages =     {783--794},
  year =      2010
}


@article{Arm05,
  author =    {Armstrong, Marc P. and Ruggles, Amy J.},
  title =     {Geographic information technologies and personal
               privacy},
  journal =   {Cartographica: The International Journal for Geographic
               Information and Geovisualization},
  publisher = {UT Press},
  volume =    40,
  number =    4,
  pages =     {63--73},
  year =      2005
}

@inproceedings{Ata03,
  title  =    {Secure and private sequence comparisons},
  author =    {Mikhail J. Atallah and Florian Kerschbaum and
               Wenliang Du},
  booktitle = {ACM Workshop on Privacy in the Electronic Society},
  address =   {Washington, DC},
  pages =     {39--44},
  year =      2003
}

@book{Bae99,
  author =    {Ricardo Baeza-Yates and Berthier Ribeiro-Neto},
  title =     {Modern Information Retrieval},
  publisher = {Addison-Wesley Longman Publishing Co.},
  address =   {Boston},
  year =      1999
}

@article{Baf13,
  title =     {The Modern Census: Evolution, Examples and
               Evaluation},
  author =    {Baffour, Bernard and King, Thomas and Valente, Paolo},
  journal =   {International Statistical Review},
  publisher = {Wiley Online Library},
  volume =    81,
  number =    3,
  pages =     {407--425},
  year =      2013
}

@book{Bal87,
  author =    {Baldwin, J. and Acheson, E.D. and Graham, W.J.},
  title =     {Textbook of medical record linkage},
  publisher = {Oxford University Press},
  year =      1987
}

@inproceedings{Bao09,
  author =    {G\'{o}mez-Bao, Jordi and Larriba-Pey, Josep-L. and
               Ribes Puig, Josepa},
  title =     {Record linkage performance for large data sets},
  booktitle = {Workshop on Privacy and Anonymity for Very Large
               Databases, held at ACM CIKM},
  pages =     {9--16},
  location =  {Hong Kong, China},
  year =      2009
}

@article{Bar09,
  author =  {Barone, D. and Maurino, A. and Stella, F. and Batini, C.},
  title =   {A Privacy-Preserving Framework for Accuracy and
             Completeness Quality Assessment},
  journal = {Emerging Paradigms in Informatics, Systems and
             Communication},
  pages =   {83},
  year =    2009
}

@inproceedings{Bar02,
  author =    {Bartolini, Ilaria and Ciaccia, Paolo and Patella,
               Marco},
  title =     {String Matching with Metric Trees Using an Approximate
               Distance},
  booktitle = {String Processing and Information Retrieval,
               LNCS 2476},
  address =   {Lisbon, Portugal},
  pages =     {271-283},
  year =      2002
}

@inproceedings{Bas02,
  author =    {John Bass},
  title =     {Statistical Linkage Keys: How effective are they?},
  booktitle = {Symposium on Health Data Linkage},
  address =   {Sydney},
  note =      {Available online at: \\
              \texttt{http://www.publichealth.gov.au/symposium.html}},
  year =      2002
}

@book{Bat06,
  author =    {Batini, C. and Scannapieco, M.},
  title =     {Data quality: Concepts, methodologies and techniques},
  series =    {Data-Centric Systems and Applications},
  isbn =      {3540331727},
  publisher = {Springer},
  year =      2006
}

@inproceedings{Bax03,
  author =    {Rohan Baxter and Peter Christen and Tim Churches},
  title =     {A Comparison of fast Blocking Methods for Record
               Linkage},
  booktitle = {ACM SIGKDD Workshop on Data Cleaning, Record Linkage
               and Object Consolidation},
  address =   {Washington DC},
  pages =     {25--27},
  year =      2003
}

@conference{Bay07,
  author =    {Bayardo, R.J. and Ma, Y. and Srikant, R.},
  title =     {Scaling up all pairs similarity search},
  booktitle = {WWW},
  address =   {Banff, Canada},
  pages =     {131--140},
  year =      2007
}

@inproceedings{Beh09,
  author =    {Alexander Behm and Shengyue Ji and Chen Li and Jiaheng
               Lu},
  title =     {Space-constrained gram-based indexing for efficient
               approximate string search},
  booktitle = {IEEE ICDE},
  address =   {Shanghai},
  pages =     {604--615},
  year =      2009
}

@article{Bel95,
  author =    {Belin, T.R. and Rubin, D.B.},
  title =     {A method for calibrating false-match rates in
               record linkage},
  journal =   {Journal of the American Statistical Association},
  publisher = {JSTOR},
  pages =     {694--707},
  year =      1995
}

@book{Bel11,
  title =     {Schema Matching and Mapping},
  author =    {Bellahsene, Z. and Bonifati, A. and Rahm, E.},
  series =    {Data-Centric Systems and Applications},
  isbn =      {3642165176},
  publisher = {Springer},
  year =      2011
}

@inproceedings{Bel12,
  author =    {Bellare, Kedar and Iyengar, Suresh and Parameswaran,
               Aditya G and Rastogi, Vibhor},
  title =     {Active sampling for entity matching},
  booktitle = {ACM SIGKDD},
  address =   {Beijing},
  pages=      {1131--1139},
  year=       2012
}

@inproceedings{Ben07,
  title =     {{D-Swoosh}: A family of algorithms for generic,
               distributed entity resolution},
  author =    {Benjelloun, O. and Garcia-Molina, H. and Gong, H.
               and Kawai, H. and Larson, T.E. and Menestrina, D.
               and Thavisomboon, S.},
  booktitle = {International Conference on Distributed Computing
               Systems},
  adress =    {Toronto, Canada},
  pages =     {37--37},
  year =      2007
}

@article{Ben09,
  title =     {Swoosh: a generic approach to entity resolution},
  author =    {Benjelloun, O. and Garcia-Molina, H. and Menestrina,
               D. and Su, Q. and Whang, S.E. and Widom, J.},
  journal =   {The VLDB Journal},
  publisher = {Springer},
  volume =    18,
  number =    1,
  pages =     {255--276},
  year =      2009
}

@inproceedings{Ber00,
  title =     {A survey of longest common subsequence algorithms},
  author =    {Bergroth, L. and Hakonen, H. and Raita, T.},
  booktitle = {String Processing and Information Retrieval},
  address =   {A Curuna, Spain},
  pages =     {39--48},
  year =      2000
}

@inproceedings{Ber03,
  author =    {Bertolazzi P, De Santis L, Scannapieco M},
  title =     {Automated record matching in cooperative information
               systems},
  booktitle = {Proceedings of the international workshop on
               data quality in cooperative information systems},
  address =   {Siena, Italy},
  year =      2003
}

@article{Ber10,
  author =   {Thomas Bernecker and Hans-Peter Kriegel and Nikos
              Mamoulis and Matthias Renz and Andreas Zuefle},
  title =    {Scalable Probabilistic Similarity Ranking in Uncertain
              Databases},
  journal =  {IEEE Transactions on Knowledge and Data Engineering},
  volume =   22,
  number =   9,
  pages =    {1234--1246},
  year =     2010
}

@article{Ber92,
  author =  {Dimitri P. Bertsekas},
  title =   {Auction Algorithms for Network Flow Problems: A Tutorial
             Introduction},
  journal = {Computational Optimization and Applications},
  volume =  1,
  pages =   {7--66},
  year =    1992
}

@article{Bha07,
  author =    {Indrajit Bhattacharya and Lise Getoor},
  title =     {Collective Entity Resolution in Relational Data},
  journal =   {ACM Transactions on Knowledge Discovery from Data},
  volume=     1,
  number=     1,
  year =      2007
}

@article{Bha07b,
  author =  {Indrajit Bhattacharya and Lise Getoor},
  title =   {Query-time entity resolution},
  journal = {Journal of Artificial Intelligence Research},
  volume =  30,
  pages =   {621--657},
  year = 2007
}

@inproceedings{Bil03,
  author =    {Mikhail Bilenko and Raymond J. Mooney},
  year =      2003,
  title =     {Adaptive duplicate detection using learnable string
               similarity measures},
  booktitle = {ACM SIGKDD},
  address =   {Washington DC},
  pages =     {39--48}
}

@inproceedings{Bil03b,
  author =    {Mikhail Bilenko and Raymond J. Mooney},
  year =      2003,
  title =     {On evaluation and training-set construction for
               duplicate detection},
  booktitle = {ACM SIGKDD workshop on Data Cleaning, Record Linkage
               and Object Consolidation},
  address =   {Washington DC},
  pages =     {7--12}
}

@inproceedings{Bil05,
  author =    {Mikhail Bilenko and Sugato Basu and Mehran Sahami},
  title =     {Adaptive Product Normalization: Using Online Learning
               for Record Linkage in Comparison Shopping},
  booktitle = {IEEE ICDM},
  address =   {Houston},
  pages =     {58--65},
  year =      2005
}

@inproceedings{Bil06,
  author =    {Mikhail Bilenko and Beena Kamath and Raymond J.
               Mooney},
  title =     {Adaptive Blocking: Learning to Scale Up Record
               Linkage},
  booktitle = {IEEE ICDM},
  address =   {Hong Kong},
  pages =     {87--96},
  year =      2006
}

@inproceedings{Bil06b,
  author =    {Bilgic, M. and Licamele, L. and Getoor, L. and
               Shneiderman, B.},
  title =     {D-Dupe: An interactive tool for entity resolution
               in social networks},
  booktitle = {IEEE Symposium on Visual Analytics Science and
               Technology},
  pages =     {43--50},
  year =      2006
}

@article{Bla02,
  author =  {Blakely T, Salmond C},
  title =   {Probabilistic record linkage and a method to calculate
             the positive predictive value},
  journal = {International Journal of Epidemiology},
  volume =  {31:6},
  pages =   {1246--1252},
  year =    2002
}

@article{Ble08,
  author =  {Bleiholder, J. and Naumann, F.},
  title =   {Data fusion},
  journal = {ACM Computing Surveys},
  volume =  41,
  number =  1,
  pages =   {1--41},
  year =    2008
}

@article{Blo70,
  author =  {Bloom, B.H.},
  title =   {Space/time trade-offs in hash coding with allowable
             errors},
  journal = {Communications of the ACM},
  volume =  13,
  number =  7,
  pages =   {422--426},
  year =    1970
}

@article{Blo95,
  title =   {Multi-source family reconstruction},
  author =  {Bloothooft, Gerrit},
  journal = {History and computing},
  volume =  7,
  number =  2,
  pages =   {90--103},
  year =    1995
}

@book{Blo15,
  title =     {Population Reconstruction},
  author =    {Bloothooft, Gerrit and Christen, Peter and
               Mandemakers, Kees and Schraagen, Marijn},
  publisher = {Springer},
  year =      2015
}

@article{Blo95b,
  title =     {Data Entry and Verification},
  author =    {Block, William C. and Star, Dianne L.},
  journal =   {Historical Methods: A Journal of Quantitative and
               Interdisciplinary History},
  publisher = {Taylor \& Francis},
  volume =    28,
  number =    1,
  pages =     {63--65},
  year =      1995
}

@inproceedings{Bon12,
  title=     {Frequent grams based embedding for privacy preserving
              record linkage},
  author=    {Bonomi, Luca and Xiong, Li and Chen, Rui and Fung,
              Benjamin},
  booktitle= {CIKM},
  address =  {Maui, Hawaii},
  pages =    {1597--1601},
  year =     2012
}

@article{Bor92,
  author =  {Borgman, Christine L. and Siegfried, Susan L.},
  title =   {Getty's Synoname$^{TM}$ and its cousins: A survey of
             applications of personal name-matching algorithms},
  journal = {Journal of the American Society for Information Science},
  volume =  43,
  number =  7,
  pages =   {459--476},
  year =    1992
}

@article{Bor01,
  title =   {Automatic segmentation of text into structured
             records},
  author =  {Borkar, V. and Deshmukh, K. and Sarawagi, S.},
  journal = {ACM SIGMOD Record},
  volume =  30,
  number =  2,
  pages =   {175--186},
  year =    2001
}

@InProceedings{Bou96,
  author =    {Bouzelat, H. and Quantin, C. and Dusserre, L.},
  title =     {Extraction and anonymity protocol of medical file},
  booktitle = {AMIA Fall Symposium},
  pages =     {323-327},
  year =      1996
}

@incollection{Boy15,
  title =     {Application of Privacy-Preserving Techniques in
               Operational Record Linkage Centres},
  author =    {Boyd, James and Randall, Sean and Ferrante,
               Anna},
  booktitle = {Medical Data Privacy Handbook},
  year =      2015
}
%%  author =    {Boyd, James H and Randall, Sean M and Ferrante,
%%               Anna M},
%%  booktitle = {Medical Data Privacy Handbook},
%%  publisher={Springer},
%%  pages =     {267--287},

@book{Bre84,
  title =     {Classification and regression trees},
  author =    {Breiman, L. and Freidman, J.H. and Olshen, R.A.
               and Stone, C.J.},
  publisher = {Chapman and Hall/CRC},
  year =      1984
}

@inproceedings{Bro03,
  author =    {Broder, A.Z. and Carmel, D. and Herscovici, M. and
               Soffer, A. and Zien, J.},
  title =     {Efficient query evaluation using a two-level
               retrieval process},
  booktitle = {ACM CIKM},
  address =   {New Orleans},
  pages =     {426--434},
  year =      2003
}

@inproceedings{Bro05,
  title =     {Reverse geocoding: Concerns about patient
               confidentiality in the display of geospatial health
               data},
  author =    {Brownstein, John S. and Cassa, Christopher and Kohane,
               Issac S. and Mandl, Kenneth D.},
  booktitle = {AMIA Annual Symposium Proceedings},
  publisher = {American Medical Informatics Association},
  pages =     905,
  year =      2005
}
%%  volume =    2005,


@article{Bro06,
  title =     {No place to hide--Reverse identification of patients
               from published maps},
  author =    {Brownstein, John S. and Cassa, Christopher and Mandl,
               Kenneth D.},
  journal =   {New England Journal of Medicine},
  publisher = {Massachusetts Medical Society},
  volume =    355,
  number =    16,
  pages =     {1741--1742},
  year =      2006
}

@article{Bro08,
  author =  {Brook, E.L. and Rosman, D.L. and Holman, C.D.A.J.},
  title =   {Public good through data linkage: measuring research
             outputs from the {Western Australian} data linkage
             system},
  journal = {Australian and New Zealand journal of public health},
  publisher={Wiley Online Library},
  volume =  32,
  number =  1,
  pages =   {19--23},
  year =    2008
}

@article{Cam08,
  author =    {Campbell, K.M. and Deck, D. and Krupski, A.},
  title =     {Record linkage software in the public domain: a
               comparison of {Link Plus}, {The Link King}, and a basic
               deterministic algorithm},
  journal =   {Health Informatics Journal},
  publisher = {SAGE Publications},
  volume =    14,
  number =    1,
  pages =     5,
  issn =      {1460--4582},
  year =      2008
}

@techreport{Can96,
  author =      {Canetti, R. and Friege, U. and Goldreich, O. and
                 Naor, M.},
  title =       {Adaptively secure multi-party computation},
  institution = {Massachusetts Institute of Technology},
  year =        1996
}

@article{Ceb05,
  author =  {Cebri{\'a}n, M. and Alfonseca, M. and Ortega, A.},
  title =   {Common pitfalls using the normalized compression distance:
             What to watch out for in a compressor},
  journal = {Communications in Information and Systems},
  volume =  5,
  pages =   {367--384},
  number =  4,
  year =    2005
}

@article{Ceg06,
  title =   {Association mining},
  author =  {Ceglar, Aaron and Roddick, John F},
  journal = {ACM CSUR},
  volume =  3,
  number =  2,
  pages =   5,
  year =    2006
}
%%  journal = {ACM Computing Surveys (CSUR)},
  
@article{Cha08,
  title =   {Regression analysis of probability-linked data},
  author =  {Chambers, R.},
  journal = {Official Statistics Research Series},
  volume =  4,
  year =    2008
}

@book{Cha10,
  author =    {Chan, Y and Talburt, J.R. and Talley, T.M.},
  title =     {Data Engineering},
  isbn =      {978-1-4419-0175-0},
  publisher = {Springer},
  year =      2010
}

@inproceedings{Cha03,
  author =    {Surajit Chaudhuri and Kris Ganjam and Venkatesh Ganti
               and Rajeev Motwani},
  title =     {Robust and Efficient Fuzzy Match for Online Data
               Cleaning},
  booktitle = {ACM SIGMOD},
  address =   {San Diego},
  pages =     {313--324},
  year =      2003
}

@inproceedings{Cha05,
author =    {Surajit Chaudhuri and Venkatesh Ganti and Rajeev
             Motwani},
title =     {Robust Identification of Fuzzy Duplicates},
booktitle = {IEEE ICDE},
address =   {Tokyo},
pages =     {865--876},
year =      2005
}

@inproceedings{Cha06,
  author =    {Chaytor, Rhonda and Brown, Edward and Wareham, Todd},
  title =     {Privacy Advisors for Personal Information Management},
  booktitle = {SIGIR Workshop on Personal Information Management},
  address =   {Seattle, Washington},
  pages =     {28--31},
  year =      2006
}

@article{Cay03,
  author =  {Cayo, Michael R. and Talbot, Thomas O.},
  title =   {Positional error in automated geocoding of residential
             addresses},
  journal = {International Journal of Health Geographics},
  volume =  2,
  number =  10,
  year =    2003
}

@article{Che04,
  author =    {Chen, H. and Chung, W. and Xu, J.J. and Wang, G. and
               Qin, Y. and Chau, M.},
  title =     {Crime data mining: a general framework and some
               examples},
  journal =   {IEEE Computer},
  publisher = {IEEE Computer Society},
  volume =    37,
  number =    4,
  pages =     {50--56},
  year =      2004
}

@article{Chi14,
  title  =  {Tracking Entities in the Dynamic World: A Fast
             Algorithm for Matching Temporal Records},
  author =  {Chiang, Yueh-Hsuan and Doan, AnHai and Naughton,
             Jeffrey F},
  journal = {PVLDB},
  volume =  7,
  number =  6,
  year =    2014
}

@article{Cho98,
  title =   {Private information retrieval},
  author =  {Chor, B. and Kushilevitz, E. and Goldreich, O. and
             Sudan, M.},
  journal = {Journal of the ACM (JACM)},
  volume =  45,
  number =  6,
  pages =   {965--981},
  year =    1998
}

@inproceedings{Chr02,
  title =     {Probabilistic name and address cleaning and
               standardization},
  author =    {Christen, P. and Churches, T. and Zhu, J.X.},
  booktitle = {Australasian Data Mining Workshop},
  address =   {Canberra},
  year =      2002
}

@inproceedings{Chr04,
  author =    {Christen, Peter and Churches, Tim and Hegland, Markus},
  title =     {Febrl -- {A} Parallel Open Source Data Linkage System},
  booktitle = {PAKDD, Springer LNAI},
  volume =    3056,
  address =   {Sydney},
  pages =     {638--647},
  year =      2004
}

@inproceedings{Chr04b,
  author =    {Christen, P. and Churches, T. and Willmore, A.},
  title =     {A probabilistic geocoding system based on a
               national address file},
  booktitle = {AusDM},
  address =   {Cairns},
  year =      2004
}

@inproceedings{Chr05,
  author =    {Peter Christen},
  title =     {Probabilistic Data Generation for Deduplication and
               Data Linkage},
  booktitle = {IDEAL, Springer LNCS},
  volume =    3578,
  address =   {Brisbane},
  pages =     {109--116},
  year =      2005
}

@inproceedings{Chr05b,
  author =    {Christen, P. and Belacic, D.},
  title =     {Automated probabilistic address standardisation and
               verification},
  booktitle = {AusDM},
  pages =     {53--67},
  address =   {Sydney},
  year =      2005
}

@inproceedings{Chr06a,
  author =    {Peter Christen},
  title =     {A Comparison of Personal Name Matching: Techniques and
               Practical Issues},
  booktitle = {Workshop on Mining Complex Data, held at IEEE
               ICDM},
  address =   {Hong Kong},
  year =      2006
}

@inproceedings{Chr06b,
  author =    {Peter Christen},
  title =     {Privacy-preserving data linkage and geocoding: Current
               approaches and research directions},
  booktitle = {Workshop on Privacy Aspects of Data Mining, held at
               IEEE ICDM},
  address =   {Hong Kong},
  year =      2006
}

@techreport{Chr06c,
  author =      {Peter Christen},
  title =       {A Comparison of Personal Name Matching: Techniques
                 and Practical Issues},
  number =      {TR-CS-07-03},
  institution = {Department of Computer Science, The Australian
                 National University},
  address =     {Canberra, Australia},
  year =        2006
}

@inproceedings{Chr07,
  author =    {Peter Christen and Karl Goiser},
  title =     {Quality and Complexity Measures for Data Linkage and
               Deduplication},
  booktitle = {Quality Measures in Data Mining},
  editor =    {Fabrice Guillet and Howard Hamilton},
  series =    {Studies in Computational Intelligence},
  publisher = {Springer},
  volume =    43,
  pages =     {127--151},
  year =      2007
}

@techreport{Chr07b,
  author =      {Peter Christen},
  title =       {Towards parameter-free blocking for scalable record
                 linkage},
  institution = {Department of Computer Science, The Australian
                 National University},
  address =     {Canberra},
  number =      {TR-CS-07-03},
  year =        2007
}

@inproceedings{Chr08b,
  author =    {Peter Christen},
  title =     {Automatic Training Example Selection for Scalable
               Unsupervised Record Linkage},
  booktitle = {PAKDD, Springer LNAI},
  volume =    5012,
  address =   {Osaka},
  pages =     {511--518},
  year =      2008
}

@inproceedings{Chr08c,
  author =    {Peter Christen},
  title =     {Automatic Record Linkage using Seeded Nearest
               Neighbour and Support Vector Machine Classification},
  booktitle = {ACM SIGKDD},
  address =   {Las Vegas},
  pages =     {151--159},
  year =      2008
}

@inproceedings{Chr08d,
  author =    {Peter Christen and Ross W. Gayler},
  title =     {Towards scalable real-time entity resolution using a
               similarity-aware inverted index approach},
  booktitle = {AusDM, CRPIT},
  volume =    87,
  address =   {Glenelg, Australia},
   pages =     {51--60},
  year =      2008
}

@inproceedings{Chr08e,
  author =    {Peter Christen},
  title =     {Febrl: An open source data cleaning, deduplication and
               record linkage system with a graphical user interface},
  booktitle = {ACM SIGKDD},
  address =   {Las Vegas},
  pages =     {1065--1068},
  year =      2008
}

@article{Chr09b,
  author =  {Peter Christen},
  title =   {Development and User Experiences of an Open Source Data
             Cleaning, Deduplication and Record Linkage System},
  journal = {SIGKDD Explorations},
  year =    2009
}
%%  number =  1,
%%  volume =  11,
%%  pages =   {39--48},


@inproceedings{Chr09,
  author =    {Peter Christen and Ross W. Gayler and David Hawking},
  title =     {Similarity-Aware Indexing for Real-Time Entity
               Resolution},
  booktitle = {ACM CIKM},
  address =   {Hong Kong},
  pages =     {1565--1568},
  year =      2009
}

@inproceedings{Chr09c,
  author =    {Peter Christen and Agus Pudjijono},
  title =     {Accurate synthetic generation of realistic personal
               information},
  booktitle = {PAKDD, Springer LNAI},
  volume =    5476, 
  address =   {Bangkok, Thailand},
  pages =     {507--514},
  year =      2009
}

@inproceedings{Chr09d,
  author =    {Christen, P.},
  title =     {Geocode Matching and Privacy Preservation},
  booktitle = {Workshop on Privacy, Security, and Trust in KDD},
  publisher=  {Springer},
  pages =     {7--24},
  year =      2009
}


@book{Chr12,
  author =    {Christen, Peter},
  title =     {Data Matching -- Concepts and Techniques for
               Record Linkage, Entity Resolution, and Duplicate
               Detection},
  publisher = {Springer},
  year =      2012
}
%%  series =    {Data-Centric Systems and Appl.},

@article{Chr12b,
  author =  {Peter Christen},
  title	=   {A Survey of Indexing Techniques for Scalable Record
             Linkage and Deduplication},
  journal = {IEEE TKDE},
  volume =  24,
  number =  9,
  pages =   {1537--1555},
  year =    2012
}
%%  journal = {IEEE Transactions on Knowledge and Data Engineering},
  
@inproceedings{Chr13,
  title =     {Adaptive Temporal Entity Resolution on Dynamic
               Databases},
  author =    {Peter Christen and Ross W. Gayler},
  booktitle = {PAKDD},
  address =   {Gold Coast, Australia},
  year =      2013
}
%%  booktitle = {PAKDD, Springer LNAI},
%%  volume =    7819,
%%  pages =     {558--569},


@inproceedings{Chr13b,
  author =    {Peter Christen and Dinusha Vatsalan},
  title =     {Flexible and extensible generation and corruption of
               personal data},
  booktitle = {ACM CIKM},
  address =   {San Francisco},
  pages =     {1165--1168},
  year =      2013
}

@InProceedings{Chr14,
  author =    {Peter Christen},
  title =     {Advanced record linkage methods and privacy aspects
               for population reconstruction},
  booktitle = {Population Reconstruction},
  Taddress =  {Amsterdam},
  year =      2014
}

@article{Chr14b,
  author =  {Christen, Peter and Vatsalan, Dinusha and Verykios,
             Vassilios S.},
  journal = {ACM Journal Data and Information Quality},
  title=    {Challenges for privacy preservation in data integration},
  year =    2014
}

@incollection{Chr15,
  title =     {Advanced Record Linkage Methods and Privacy Aspects
               for Population Reconstruction--A Survey and Case
               Studies},
  author =    {Christen, Peter and Vatsalan, Dinusha and Fu, Zhichun},
  booktitle = {Population Reconstruction},
  pages =     {87--110},
  publisher = {Springer},
  year=       2015,
}

@article{Chu02,
  author =  {Tim Churches and Peter Christen and Kim Lim and Justin X.
             Zhu},
  title	=   {Preparation of Name and Address Data for Record Linkage
             using Hidden {Markov} Models},
  journal = {BMC Med Inform Decis Mak},
  volume =  2,
  number =  9,
  year =    2002
}

@article{Chu03,
  author =  {Churches, Tim},
  title =   {A proposed architecture and method of operation for
             improving the protection of privacy and confidentiality
             in disease registers},
  journal = {BMC Med Res Methodol},
  volume =  3,
  number =  1,
  year =    2003,
}

@article{Chu04,
  author =  {Churches, Tim and Christen, Peter},
  title =   {Some Methods for Blindfolded Record Linkage},
  journal = {BioMed Central Medical Informatics and Decision Making},
  volume =  4,
  number =  9,
  year =    2004
}

@inproceedings{Chu04b,
  author =    {Churches, Tim and Christen, Peter},
  title =     {Blind data linkage using n-gram similarity
               comparisons},
  booktitle = {PAKDD, Springer LNAI},
  volume =    3056,
  address =   {Sydney},
  pages =     {121--126},
  year =      2004
}

@article{Cil05,
  author    = {Cilibrasi, Rudi and Vit{\'a}nyi, Paul M.B.},
  title     = {Clustering by compression},
  journal   = {IEEE Transactions on Information Theory},
  volume    = 51,
  number    = 4,
  pages     = {1523--1545},
  year      = 2005
}

@article{Cla04,
  author =  {David E Clark},
  title =   {Practical Introduction to Record Linkage for Injury
             Research},
  journal = {Injury Prevention},
  volume =  10,
  pages =   {186--191},
  year =    2004
}

@inproceedings{Cli04,
  author =    {Clifton, Chris and Kantarcioglu, Murat and Doan,
               AnHai and Schadow, Gunther and Vaidya, Jaideep and
               Elmagarmid, Ahmed and Suciu, Dan},
  title =     {Privacy-preserving data integration and sharing},
  booktitle = {ACM SIGMOD workshop on Research issues in Data Mining
               and Knowledge Discovery},
  location =  {Paris},
  pages =     {19-26},
  year =      2004
}

@article{Coc01,
  title =   {Efficient data reconciliation},
  author =  {Cochinwala, M. and Kurien, V. and Lalk, G. and
             Shasha, D.},
  journal = {Information Sciences},
  publisher={Elsevier},
  volume =  137,
  number =  {1--4},
  pages =   {1--15},
  year =    2001
}

@inproceedings{Coh98,
  author =    {William W. Cohen},
  title =     {Integration of heterogeneous databases without common
               domains using queries based on textual similarity},
  booktitle = {ACM SIGMOD},
  address =   {Seattle},
  pages =     {201--212},
  year =      1998
}

@article{Coh98b,
  title =   {The {WHIRL} approach to data integration},
  author =  {Cohen, W.W.},
  journal = {IEEE Intelligent Systems},
  volume =  13,
  number =  3,
  pages =   {20--24},
  year =    1998
}

@article{Coh00,
  author =  {Cohen, W.W.},
  title =   {Data integration using similarity joins and a
             word-based information representation language},
  journal = {ACM Transactions on Information Systems},
  volume =  18,
  number =  3,
  pages =   {288--321},
  year =    2000
}

@inproceedings{Coh02,
  author =    {William W. Cohen and Jacob Richman},
  title =     {Learning to Match and Cluster Large High-dimensional
               Data Sets for Data Integration},
  booktitle = {ACM SIGKDD},
  address =   {Edmonton},
  pages =     {475--480},
  year =      2002
}

@inproceedings{Coh03,
  author =    {William W. Cohen and Ravikumar, P. and Fienberg, S.E.},
  title =     {A comparison of string distance metrics for
               name-matching tasks},
  booktitle = {Workshop on Information Integration on the Web, held at
               IJCAI},
  address =   {Acapulco},
  pages =     {73--78},
  year =      2003
}

@inproceedings{Con03,
  author =    {Conrad, J. G. and Guo, X. S and Schriber, C. P.},
  title =     {Online duplicate detection: Signature reliability in a
               dynamic retrieval environment},
  booktitle = {ACM CIKM},
  address =   {New Orleans},
  pages =     {443--452},
  year =      2003
}

@article{Cur06,
  title =     {Spatial confidentiality and {GIS}: {Re-engineering}
               mortality locations from published maps about
               {Hurricane Katrina}},
  author =    {Curtis, Andrew J. and Mills, Jacqueline W. and Leitner,
               Michael},
  journal =   {International Journal of Health Geographics},
  volume =    5,
  number =    1,
  pages =     {44--56},
  publisher = {BioMed Central},
  year =      2006
}

@inproceedings{Dal11,
  author =    {Dal Bianco, G. and Galante, R. and Heuser, C.A.},
  title =     {A fast approach for parallel deduplication on multicore
               processors},
  booktitle = {ACM Symposium on Applied Computing},
  pages =     {1027--1032},
  year =      2011
}

@article{Dam64,
  author =  {Damerau, Fred J.},
  title =   {A technique for computer detection and correction of
             spelling errors},
  journal = {Communications of the ACM},
  volume =  7,
  number =  3,
  pages =   {171--176},
  year =    1964
}

@techreport{Day95,
  title =       {Record linkage I: evaluation of commercially
                 available record linkage software for use in {NASS}},
  author =      {Day, Charles},
  institution = {National Agricultural Statistics Service},
  number =      {STB Research Report STB-95-02},
  address =     {Washington DC},
  year =        1995
}

@inproceedings{DeV09,
  author =    {de Vries, T. and Ke, H. and Chawla, S. and Christen,
               P.},
  title =     {Robust record linkage blocking using suffix arrays},
  booktitle = {ACM CIKM},
  address =   {Hong Kong},
  pages =     {305--314},
  year =      2009
}

@article{DeV11,
  author =    {de Vries, Timothy and Ke, Hui and Chawla, Sanjay and
               Christen, Peter},
  title =     {Robust record linkage blocking using suffix arrays
               and {Bloom} filters},
  journal =   {ACM Transactions on Knowledge Discovery from Data},
  volume =    5,
  number =    2,
  year =      2011
}

@article{Dey10,
  title =   {Efficient Techniques for Online Record Linkage},
  author =  {Dey, Debabrata and Mookerjee, Vijay S. and Liu, Dengpan},
  journal = {IEEE Transactions on Knowledge and Data Engineering},
  volume =  23,
  number =  3,
  pages =   {373--387},
  year =    2010
}

@article{Dom03,
  author =    {Domingo-Ferrer, J. and Torra, V.},
  title =     {Disclosure risk assessment in statistical microdata
               protection via advanced record linkage},
  journal =   {Statistics and Computing},
  publisher = {Springer},
  volume =    13,
  number =    4,
  pages =     {343--354},
  year =      2003
}

@inproceedings{Don05,
  author =   {Dong, Xin L. and Halevy, Alon and Madhavan, Jayant},
  title=     {Reference reconciliation in complex information spaces},
  booktitle= {ACM SIGMOD},
  address =  {Baltimore},
  year=      2005
}
%%  pages =    {85--96},

@article{Don09,
  title =     {Data integration with uncertainty},
  author =    {Dong, X.L. and Halevy, A. and Yu, C.},
  journal =   {The VLDB Journal},
  publisher = {Springer},
  volume =    18,
  number =    2,
  pages =     {469--500},
  year=       2009
}

@article{Don15,
  title =     {Big Data integration},
  author =    {Dong, Xin Luna and Srivastava, Divesh},
  journal =   {Synthesis Lectures on Data Management},
  volume =    7,
  number =    1,
  pages =     {1--198},
  publisher = {Morgan and Claypool Publishers},
  year =      2015
}

@inproceedings{Dra09,
  author =   {Draisbach, Uwe and Naumann, Felix},
  title =    {A Comparison and Generalization of Blocking and
              Windowing Algorithms for Duplicate Detection},
  booktitle= {Workshop on Quality in Databases, held at VLDB},
  address =  {Lyon},
  year =     2009
}

@inproceedings{Dra10,
  author =    {Draisbach, U. and Naumann, F.},
  title =     {DuDe: The duplicate detection toolkit},
  booktitle = {Workshop on Quality in Databases, held at VLDB},
  address =   {Singapore},
  year =      2010
}

@inproceedings{Dra12,
  title =     {Adaptive windows for duplicate detection},
  author =    {Draisbach, Uwe and Naumann, Felix and Szott,
               Sascha and Wonneberg, Oliver},
  booktitle = {IEEE ICDE},
  address =   {Washington, DC},
  pages =     {1073--1083},
  year =      2012
}

@inproceedings{Du00,
  title =     {Protocols for secure remote database access with
               approximate matching},
  author =    {Du, W. and Atallah, M.J. and Kerschbaum, F.},
  booktitle = {First ACM Workshop on Security and Privacy in
               E-Commerce},
  year =       2000
}

@article{Dun46,
  author =  {Dunn, H.L.},
  title =   {Record linkage},
  journal = {American Journal of Public Health},
  publisher={Am Public Health Assoc},
  volume =  36,
  number =  12,
  pages =   1412,
  year =    1946
}

@article{Dur11,
  title =   {Quantifying the correctness, computational complexity,
             and security of privacy-preserving string comparators
             for record linkage},
  author =  {Durham, Elizabeth A. and Xue, Yuan and Kantarcioglu,
             Murat and Malin, Bradley},
  journal = {Information Fusion},
  volume =  13,
  number =  4,
  pages =   {245--259},
  year =    2012
}

@PhdThesis{Dur12,
  author =  {Durham, Elizabeth A.},
  title =   {A Framework for Accurate, Efficient Private Record
             Linkage},
  school =  {Faculty of the Graduate School of Vanderbilt
             University},
  address = {Nashville, TN},
  year =    2012
}

@article{Dur14,
  title =   {Composite {Bloom} filters for secure record linkage},
  author =  {Durham, Elizabeth A and Kantarcioglu, Murat and
             Xue, Yuan and Toth, Csaba and Kuzu, Mehmet and
             Malin, Bradley},
  journal = {IEEE TKDE},
  volume =  26,
  number =  12,
  pages =   {2956--2968},
  year =    2014
}

@article{Dus95,
  author =  {Dusserre, L. and Quantin, C. and Bouzelat, H.},
  title =   {A one way public key cryptosystem for the linkage of
             nominal files in epidemiological studies},
  journal = {Medinfo},
  volume =  8,
  pages =   {644--647},
  year =    1995
}

@article{Dwo06,
  title =     {Differential privacy},
  author =    {Dwork, C.},
  journal =   {Automata, languages and programming},
  publisher = {Springer},
  pages =     {1--12},
  year =      2006
}

@incollection{Efr14,
  author =    {Efremova, Julia and Ranjbar-Sahraei, Bijan and
               Oliehoek, Frans A and Calders, Toon and Tuyls, Karl},
  editor =    {Gerrit Bloothooft and Peter Christen and Kees
               Mandemakers and Marijn Schraagen},
  booktitle = {Population Reconstruction},
  title =     {A baseline method for genealogical entity resolution},
  publisher = {Springer},
  year =      2015,
}

@inproceedings{Elf02,
  author =    {Mohamed G. Elfeky and Vassilios S. Verykios and Ahmed
               K. Elmagarmid},
  title =     {{TAILOR}: A Record Linkage Toolbox},
  booktitle = {IEEE ICDE},
  address =   {San Jose},
  pages =     {17--28},
  year =      2002
}

@article{Elm07,
  author =  {Elmagarmid,  Ahmed K. and Ipeirotis, Panagiotis G. and
             Verykios, Vassilios S.},
  title =   {Duplicate Record Detection: A Survey},
  journal = {IEEE TKDE},
  volume =  19,
  number =  1,
  pages =   {1--16},
  year =    2007
}

@article{Fag96,
  title =   {Comparing information without leaking it},
  author =  {Fagin, R. and Naor, M. and Winkler, P.},
  journal = {Communications of the ACM},
  volume =  39,
  number =  5,
  pages =   {77--85},
  year =    1996
}

@inproceedings{Fal95,
  author =    {Christos Faloutsos and King-Ip Lin},
  title =     {{Fastmap}: A fast Algorithm for Indexing, Data-Mining
               and Visualization of Traditional and Multimedia
               Datasets},
  booktitle = {ACM SIGMOD},
  address =   {San Jose},
  pages =     {163--174},
  year =      1995
}

@techreport{Faw04,
  author =      {{Fawcett T}},
  year =        2004,
  title =       {{ROC Graphs}: Notes and practical considerations for
                 researchers},
  institution = {HP Laboratories},
  number =      {HPL-2003-4},
  address =     {Palo Alto}
}

@article{Fel76,
  author =    {Ivan P. Fellegi and Holt, D.},
  title =     {A systematic approach to automatic edit and
               imputation},
  journal =   {Journal of the American Statistical Association},
  publisher = {JSTOR},
  pages =     {17--35},
  year =      1976
}

@article{Fel69,
  author =  {Ivan P. Fellegi and Alan B. Sunter},
  title =   {A Theory for Record Linkage},
  journal = {Journal of the American Statistical Association},
  volume =  64,
  number =  328,
  pages =   {1183--1210},
  year =    1969
}

@inproceedings{Fie04,
  author =    {Fienberg, S.E. and McIntyre, J.},
  title =     {Data swapping: Variations on a theme by {Dalenius
               and Reiss}},
  booktitle = {Privacy in Statistical Databases, Springer LNCS
               3050},
  pages =     {14--29},
  year =      2004
}

@article{Fie05,
  author =  {Fienberg, Stephen E.},
  title =   {Homeland insecurity: Datamining, terrorism detection,
             and confidentiality},
  journal = {Bull. Internat. Stat. Inst},
  year =    2005
}

@article{Fie05b,
  title =   {Confidentiality and disclosure limitation},
  author =  {Fienberg, Stephen E},
  journal = {Encyclopedia of Social Measurement},
  volume =  1,
  pages =   {463--69},
  year =    2005
}

@article{Fie06,
  title =     {Privacy and confidentiality in an e-Commerce
               world: Data mining, data warehousing, matching
               and disclosure limitation},
  author =    {Fienberg, S.E.},
  journal =   {Statistical Science},
  publisher = {Institute of Mathematical Statistics},
 volume =     21,
  number =    2,
  pages =     {143--154},
  year =      2006
}

@inproceedings{Fis15,
  title={Unsupervised Measuring of Entity Resolution Consistency},
  author={Fisher, Jeffrey and Wang, Qing},
  booktitle={IEEE ICDM DINA Workshop},
  pages={218--221},
  year={2015},
}

@article{Fog93,
  author =    {Fogel, R.W.},
  title=      {New Sources and New Techniques for the Study of
               Secular Trends in Nutritional Status, Health,
               Mortality, and the Process of Aging},
  journal =   {NBER Historical Working Papers},
  publisher = {National Bureau of Economic Research, Inc},
  year =      1993
}

@article{For01,
  author =  {Fortini, M. and Liseo, B. and Nuccitelli, A. and
             Scanu, M.},
  title =   {On {Bayesian} record linkage},
  journal = {Research in Official Statistics},
  volume =  4,
  number =  1,
  pages =   {185--198},
  year =    2001
}

@article{Fra09,
  title =     {Communication-efficient private protocols for
               longest common subsequence},
  author =    {Franklin, M. and Gondree, M. and Mohassel, P.},
  journal =   {Topics in Cryptology--CT-RSA},
  pages =     {265--278},
  publisher = {Springer},
  year =      2009
}

@article{Fri92,
  author =  {Friedman, Carol and Sideli, Robert},
  title =   {Tolerating Spelling Errors during Patient validation},
  journal = {Computers and Biomedical Research},
  volume =  25,
  pages =   {486--509},
  year =    1992
}

@inproceedings{Fu11a,
  author =    {Zhichun Fu and Peter Christen and Mac Boot},
  title =     {Automatic Cleaning and Linking of Historical
               Census Data using Household Information},
  booktitle = {Workshop on Domain Driven Data Mining, held at IEEE
               ICDM},
  address =   {Vancouver},
  year =      2011
}

@inproceedings{Fu11,
  author =    {Zhichun Fu and Peter Christen and Mac Boot},
  title =     {A Supervised Learning and Group Linking Method
               for Historical Census Household Linkage},
  booktitle = {AusDM, CRPIT},
  volume =    121,
  address =   {Ballarat, Australia},
  year =      2011
}

@inproceedings{Fu12,
  author =    {Zhichun Fu and Jun Zhou and Peter Christen and
               Mac Boot},
  title =     {Multiple Instance Learning for Group Record Linkage},
  booktitle = {PAKDD},
  address =   {Kuala Lumpur, Malaysia},
  year =      2012
}
%%  booktitle = {PAKDD, Springer LNAI},
%%  volume =    7301,
%%  pages =     {171--182},

@article{Fu14,
  author =       {Zhichun Fu and Mac Boot and Peter Christen and
                  Jun Zhou},
  title =        {Automatic Record Linkage of Individuals and
                  Households in Historical Census Data},
  journal =      {International Journal of Humanities and Arts
                  Computing},
  organization = {Edinburgh University Press},
  year =         2014
}

@inproceedings{Fu14b,
  author =    {Zhichun Fu and Peter Christen and Jun Zhou},
  title =     {A Graph Matching Method for Historical Census
               Household Linkage},
  booktitle = {PAKDD},
  address =   {Tainan},
  year =      2014
}
%%  booktitle = {PAKDD, Springer LNAI},
%%  volume =    8443,
%%  pages=      {485--496},

@article{Fur00,
  title =   {Interactive record linkage: The cumulative construction
             of life courses},
  author =  {Fure, Eli},
  journal = {Demographic Research},
  volume =  3,
  number =  11,
  pages =   {3--11},
  year =    2000
}

@inproceedings{Gal00,
  author =    {Helena Galhardas and Daniela Florescu and
               Dennis Shasha and Eric Simon},
  year =      2000,
  title =     {An extensible framework for data cleaning},
  booktitle = {IEEE ICDE},
  address =   {San Diego},
}
%  pages =     {312}

@inproceedings{Gil97,
  author =    {Leicester Gill},
  title =     {{OX-LINK}: The {Oxford} Medical Record Linkage System},
  booktitle = {Proc. Int’l Record Linkage Workshop and Exposition},
  address =   {Arlington, Virginia},
  pages =     {15--33},
  year =      1997
}

@techreport{Gil01,
  author =      {Leicester Gill},
  title =       {Methods for Automatic Record Matching and Linking
                 and their use in National Statistics},
  number =      {Methodology Series, no.\ 25},
  institution = {National Statistics},
  address =     {London},
  year =        2001
}

@article{Giu07,
  author =       {Giunchiglia, F. and Yatskevich, M. and Shvaiko, P.},
  title =        {Semantic matching: Algorithms and implementation},
  journal =      {Journal on Data Semantics IX},
  pages =        {1--38},
  organization = {Springer-Verlag},
  year = 2007
}

@article{Gla08,
  author =  {Glasson, Emma and De Klerk, Nick and Bass, John and
             Rosman, Diana and Palmer, Lyle J. and Holman, D'Arcy},
  title =   {Cohort profile: the {Western Australian} family
             connections genealogical project},
  journal = {International Journal of epidemiology},
  publisher={IEA},
  volume =  37,
  number =  1,
  pages =   {30--35},
  year =    2008
}

@Book{Gli10,
  editor =    {Gliklich, R.E. and Dreyer, N.A.},
  title =     {Registries for Evaluating Patient Outcomes: A
               User’s Guide},
  publisher = {AHRQ Publication},
  number =    {No.10-EHC049},
  year =      2010
}

@inproceedings{Goi06,
  author =    {Karl Goiser and Peter Christen},
  title =     {Towards Automated Record Linkage},
  booktitle = {AusDM, CRPIT},
  volume =    61,
  pages =     {23--31},
  address =   {Sydney},
  year =      2006
}


@techreport{Gol02,
  author =      {Goldreich, O.},
  title =       {Secure multi-party computation},
  institution = {Department of Computer Science and Applied
                 Mathematics, Weizmann Institute of Science,
                 Israel},
  year =        2002
}

@article{Gom02,
  author =    {Gomatam, S. and Carter, R. and Ariet, M. and
               Mitchell, G.},
  title =     {An empirical comparison of record linkage procedures},
  journal =   {Statistics in Medicine},
  publisher = {Wiley Online Library},
  volume =    21,
  number =    10,
  pages =     {1485--1496},
  issn =      {1097-0258},
  year =      2002
}

@article{Gon06,
  author =  {Gong, Ruibin and Chan, Tony K.Y.},
  title =   {Syllable alignment: A novel model for phonetic string
             search},
  journal = {IEICE Transactions on Information and Systems},
  volume =  {E89-D},
  number =  1,
  pages =   {332--339},
  year =    2006
}

@inproceedings{Gra01,
  author =    {Luis Gravano and Panagiotis G. Ipeirotis and H. V.
               Jagadish and Nick Koudas and S. Muthukrishnan and
               Divesh Srivastava},
  title =     {Approximate String Joins in a Database (Almost) for
               Free},
  booktitle = {VLDB},
  address =   {Roma},
  pages =     {491--500},
  year =      2001
}

@inproceedings{Gu04,
  author =    {Gu, L. and Baxter, R.},
  title =     {Adaptive filtering for efficient record linkage},
  booktitle = {SIAM international conference on data mining},
  address =   {Orlando, Florida},
  year =      2004
}

@inproceedings{Gu06,
  author =    {Gu, L. and Baxter, R.},
  title =     {Decision models for record linkage},
  booktitle = {Selected Papers from AusDM, Springer LNCS 3755},
  pages =     {146--160},
  year =      2006
}

@inproceedings{Guo09,
  author =    {Guo, H. and Zhu, H. and Guo, Z. and Zhang, X.X.
               and Su, Z.},
  title =     {Address standardization with latent semantic
               association},
  booktitle = {ACM SIGKDD},
  address =   {Paris},
  pages =     {1155--1164},
  year =      2009}

@inproceedings{Haj10,
  author =    {Hajishirzi, H. and Yih, W. and Kolcz, A.},
  title =     {Adaptive near-duplicate detection via similarity
               learning},
  booktitle=  {ACM SIGIR},
  pages =     {419--426},
  address =   {Geneva, Switzerland},
  year =      2010
}

@article{Hal09,
  author =  {Hall, M. and Frank, E. and Holmes, G. and Pfahringer,
             B. and Reutemann, P. and Witten, I.H.},
  title =   {The {WEKA} data mining software: an update},
  journal = {ACM SIGKDD Explorations},
  volume =  11,
  number =  1,
  pages =   {10--18},
  year =    2009
}

@article{Hal80,
  author =  {Hall, Patrick A.V. and Dowling, Geoff R.},
  title =   {Approximate string matching},
  journal = {ACM Computing Surveys},
  volume =  12,
  number =  4,
  pages =   {381--402},
  year =    1980
}

@inproceedings{Hal10,
  title =     {Privacy-preserving record linkage},
  author =    {Hall, R. and Fienberg, S.},
  booktitle = {Privacy in Statistical Databases, Springer
               LNCS 6344},
  address =   {Corfu, Greece},
  pages =     {269--283},
  year =      2010
}

@book{Han06,
  title =     {Data mining: concepts and techniques},
  author=     {Han, J. and Kamber, M.},
  publisher = {Morgan Kaufmann},
  edition =   2,
  year=       2006
}

@article{Han06b,
  author =   {Hand, D.J.},
  title =    {Classifier technology and the illusion of progress},
  journal =  {Statistical Science},
  publisher ={Institute of Mathematical Statistics},
  volume =   21,
  number =   1,
  pages =    {1--14},
  year =     2006
}

@article{Han18,
  title={A note on using the {F}-measure for evaluating record
         linkage algorithms},
  author={Hand, David and Christen, Peter},
  journal={Statistics and Computing},
  volume={28},
  number={3},
  pages={539--547},
  year={2018},
  publisher={Springer}
}

@inproceedings{Har04,
  author =    {Harada, M. and Sato, S. and Kazama, K.},
  title =     {Finding authoritative people from the Web},
  booktitle = {ACM/IEEE-CS joint conference on Digital Libraries},
  address =   {Tucson},
  pages =     {306--313},
  year =      2004
}

@article{Has09,
  author =    {Hassanzadeh, O. and Miller, R.J.},
  title =     {Creating probabilistic databases from duplicated data},
  journal =   {The VLDB Journal},
  publisher = {Springer},
  volume =    18,
  number =    5,
  pages =     {1141--1166},
  year =      2009
}

@inproceedings{Has09b,
  author =    {Hassanzadeh, O. and Kementsietsidis, A. and Lim, L.
               and Miller, R.J. and Wang, M.},
  title =     {A framework for semantic link discovery over
               relational data},
  booktitle = {ACM CIKM},
  address =   {Hong Kong},
  pages =     {1027--1036},
  year =      2009
}

@article{Hec97,
  title =     {Bayesian networks for data mining},
  author =    {Heckerman, D.},
  journal =   {Data mining and knowledge discovery},
  publisher = {Springer},
  volume =    1,
  number =    1,
  pages =     {79--119},
  year =      1997
}

@inproceedings{Hen06,
  author =    {Henzinger, Monika},
  title =     {Finding near-duplicate web pages: a large-scale
               evaluation of algorithms},
  booktitle = {ACM SIGIR},
  address =   {Seattle},
  year =      2006
}
%%  pages =     {284--291},


@inproceedings{Her95,
  author =    {Mauricio A. Hernandez and Salvatore J. Stolfo},
  title =     {The merge/purge problem for large databases},
  booktitle = {ACM SIGMOD},
  address =   {San Jose},
  pages =     {127--138},
  year  =     1995
}



@article{Her98,
  author =    {Mauricio A. Hernandez and Salvatore J. Stolfo},
  title =     {Real-world data is dirty: Data cleansing and the
               merge/purge problem},
  journal =   {Data Mining and Knowledge Discovery},
  publisher = {Kluwer Academic Publishers},
  volume =    2,
  number =    1,
  pages =     {9--37},
  year  =     1998
}

@article{Her11,
  author =    {Herschel, M. and Naumann, F. and Szott, S. and
               Taubert, M.},
  title =     {Scalable Iterative Graph Duplicate Detection},
  journal =   {IEEE  Transactions on Knowledge and Data Engineering},
  volume =    "X",
  number =    "Y",
  year =      2011
}

@book{Her07,
  author =    {Herzog, Thomas N. and Scheuren, Fritz J. and Winkler,
               William E.},
  title =     {Data quality and record linkage techniques},
  publisher = {Springer},
  year =      2007
}

@article{Hir05,
  author =    {Hirsch, J.E.},
  title =     {An index to quantify an individual's scientific
               research output},
  journal =   {Proceedings of the National Academy of Sciences of
               the United States of America},
  publisher = {National Academy of Sciences},
  volume =    102,
  number =    46,
  pages =     {16569--16572},
  year =      2005
}

@inproceedings{Hol02,
  author =    {Holmes, David and McCabe, Catherine M.},
  title =     {Improving precision and recall for {Soundex}
               retrieval},
  booktitle = {Proceedings of the IEEE International Conference on
               Information Technology -- Coding and Computing},
  address =   {Las Vegas},
  year =      2002
}

@article{Ioa10,
  author =  {Ioannou, Ekaterini and Nejdl, Wolfgang and
             Nieder{\'e}e, Claudia and Velegrakis, Yannis},
  title =   {On-the-Fly Entity-Aware Query Processing in the
             Presence of Linkage},
  journal = {VLDB Endowment},
  volume =  3,
  number =  1,
  year =    2010
}

@inproceedings{Ina08,
  title =     {A hybrid approach to private record linkage},
  author =    {Ali Inan and Murat Kantarcioglu and Elisa Bertino and
               Monica Scannapieco},
  booktitle = {IEEE ICDE},
  address =   {Cancun, Mexico},
  pages =     {496--505},
  year =      2008
}

@inproceedings{Ind98,
  title =     {Approximate nearest neighbors: towards removing the
               curse of dimensionality},
  author =    {Indyk, Piotr and Motwani, Rajeev},
  address =   {Dallas},
  booktitle = {ACM TOC},
  pages =     {604--613},
  year =      1998
}

@inproceedings{Ina10,
  title =        {Private record matching using differential privacy},
  author =       {Ali Inan and Murat Kantarcioglu and Gabriel Ghinita
                  and Elisa Bertino},
  booktitle =    {EDBT},
  address =      {Lausanne, Switzerland},
  pages =        {123--134},
  year =         2010
}

@article{Jar89,
  author =  {Jaro, Matthew A.},
  title =   {Advances in Record-linkage Methodology a applied to
             matching the 1985 {Census of Tampa, Florida}},
  journal = {Journal of the American Statistical Association},
  volume =  84,
  pages =   {414--420},
  year =    1989
}

@inproceedings{Jen10,
  author =    {Jentzsch, A. and Isele, R. and Bizer, C.},
  title =     {Silk--Generating {RDF} Links while publishing or
               consuming Linked Data},
  booktitle = {Poster at the International Semantic Web Conference},
  address =   {Shanghai},
  year =      2010
}

@inproceedings{Jha08,
  title =     {Towards practical privacy for genomic computation},
  author =    {Jha, S. and Kruger, L. and Shmatikov, V.},
  booktitle = {IEEE Symposium on Security and Privacy},
  address =   {Oakland},
  pages =     {216--230},
  year =      2008
}

@inproceedings{Jin03,
  author =    {Liang Jin and Chen Li and Sharad Mehrotra},
  title =     {Efficient Record Linkage in Large Data Sets},
  booktitle = {DASFAA},
  address =   {Tokyo},
  pages =     {137--146},
  year =      2003
}

@inproceedings{Jol11,
  author =    {Joly, Alexis and Buisson, Olivier},
  title =     {Random maximum margin hashing},
  booktitle = {IEEE CVPR},
  address =   {Colorado Springs},
  pages =     {873--880},
  year =      2011
}
%% {Computer Vision and Pattern Recognition (CVPR), 2011 IEEE
%% Conference on},


@article{Jok96,
  author =  {Jokinen, Petteri and Tarhio, Jorma and Ukkonen, Esko},
  title =   {A comparison of approximate string matching algorithms},
  journal = {Software -- Practice and Experience},
  volume =  26,
  number =  12,
  pages =   {1439--1458},
  year =    1996
}

@article{Jon06,
  author =  {Jeff Jonas and Jim Harper},
  title =   {Effective Counterterrorism and the Limited Role of
             Predictive Data Mining},
  journal = {Policy Analysis},
  number =  584,
  year =    2006
}

@inproceedings{Jur08,
  title =        {{FRIL}: A tool for comparative record linkage},
  author =       {Jurczyk, P. and Lu, J.J. and Xiong, L. and Cragan,
                  J.D. and Correa, A.},
  booktitle =    {AMIA Annual Symposium Proceedings},
  organization = {American Medical Informatics Association},
  pages =        440,
  year =         2008
}

@article{Kal06,
  title =   {Domain-independent data cleaning via analysis of
             entity-relationship graph},
  author =  {Kalashnikov, Dmitri V. and Mehrotra, Sharad},
  journal = {ACM ToDS},
  volume =  31,
  number =  2,
  pages =   {716--767},
  year =    2006
}

@article{Kan08,
  title =   {Interactive Entity Resolution in Relational Data: A
             Visual Analytic Tool and Its Evaluation},
  author =  {Kang, Hyunmo and Getoor, Lise and Shneiderman, Ben
             and Bilgic, Mustafa and Licamele, Louis},
  journal = {IEEE Transactions on Visualization and Computer
             Graphics},
  number =  5,
  volume =  14,
  pages =   {999--1014},
  year =    2008
}

@article{Kan09,
  title =     {Formal anonymity models for efficient privacy-preserving
               joins},
  author =    {Kantarcioglu, M. and Inan, A. and Jiang, W. and
               Malin, B.},
  journal =   {Data and Knowledge Engineering},
  publisher = {Elsevier},
  pages =     {1206--1223},
  volume =    68,
  number =    11,
  year =      2009
}

@inproceedings{Kar09,
  title =        {Privacy Preserving Record Linkage Using Phonetic
                  Codes},
  author =       {Karakasidis, Alexandros and Verykios, Vassilios S.},
  booktitle =    {Fourth Balkan Conference in Informatics},
  organization = {IEEE},
  address =      {Thessaloniki, Greece},
  pages =        {101--106},
  year =         2009
}

@inproceedings{Kar10,
  title =        {Advances in Privacy Preserving Record Linkage},
  author =       {Karakasidis, Alexandros and Verykios, Vassilios S.},
  booktitle =    {E-activity and Innovative Technology, Advances in
                  Applied Intelligence Technologies Book Series },
  organization = {IGI Global},
  pages =        {22--34},
  year =         2010
}

@article{Kar11,
  title =   {Secure Blocking + Secure Matching = Secure
             Record Linkage},
  author =  {Karakasidis, A. and Verykios, V.S.},
  journal = {Journal of Computing Science and Engineering},
  volume =  5,
  number =  3,
  year =    2011
}

@inproceedings{Kar11b,
  title =        {Fake Injection Strategies for Private Phonetic
                  Matching},
  author =       {Karakasidis, Alexandros and Verykios, Vassilios S.
                  and Christen, Peter},
  booktitle =    {International Workshop on Data Privacy Management},
  address =      {Leuven, Belgium},
  year =         2011
}

@inproceedings{Kar12,
  title =     {Reference table based k-anonymous private blocking},
  author =    {Karakasidis, Alexandros and Verykios, Vassilios S},
  booktitle = {ACM Symposium on Applied Computing},
  address =   {Trento, Italy},
  pages =     {859--864},
  year =      2012
}

@article{Kar14,
  title =   {An {LSH}-based Blocking Approach with a Homomorphic
             Matching Technique for Privacy-Preserving Record Linkage},
  author =  {Karapiperis, Dimitrios and Verykios, Vassilios S},
  journal = {IEEE Transactions on Knowledge and Data Engineering},
  year=     2014
}

@techreport{Kaw06,
  author =      {Kawai, H. and Garcia-Molina, H. and Benjelloun, O.
                 and Menestrina, D. and Whang, E. and Gong, H.},
  title =       {{P-Swoosh}: Parallel algorithm for generic entity
                 resolution},
  number =      {2006-19},
  institution = {Department of Computer Science, Stanford
                 University},
  year =        2006
}

@inproceedings{Kej13,
  title =     {An Unsupervised Algorithm for Learning Blocking
  Schemes},
  author =    {Kejriwal, Mayank and Miranker, Daniel P},
  booktitle = {IEEE ICDM},
  address = {Dallas},
  pages={340--349},
  year={2013},
}



@article{Kel02,
  author =  {Chris W. Kelman and John Bass and D'Arcy Holman},
  title =   {Research use of Linked Health Data -- {A} Best Practice
             Protocol},
  journal = {Aust NZ Journal of Public Health},
  volume =  26,
  pages =   {251--255},
  year =    2002
}

@inproceedings{Kes03,
  author =    {Keskustalo, Heikki and Pirkola, Ari and Visala, Kari
               and Leppanen, Erkka and Jarvelin, Kalervo},
  title =     {Non-adjacent Digrams Improve Matching of Cross-Lingual
               Spelling Variants},
  booktitle = {String Processing and Information Retrieval, LNCS
               2857},
  address =   {Manaus, Brazil},
  pages =     {252--265},
  year =      2003
}

@inproceedings{Kim07,
  author =    {Kim, H. and Lee, D.},
  title =     {Parallel linkage},
  booktitle = {ACM CIKM},
  address =   {Lisboa, Portugal},
  pages =     {283--292},
  year =      2007
}

@inproceedings{Kim10,
  author =    {Kim, H. and Lee, D.},
  title =     {{HARRA}: fast iterative hashed record linkage for
               large-scale data collections},
  booktitle = {EDBT},
  address =   {Lausanne},
  pages =     {525--536},
  year =      2010
}

@article{Kir10,
  author =  {Kirsten, T. and Kolb, L. and Hartung, M. and Gross,
             A. and K\"opcke, H. and Rahm, E.},
  title =   {Data Partitioning for Parallel Entity Matching},
  journal = {Proceedings of the VLDB Endowment},
  volume =  3,
  number=   2,
  year =    2010
}

@article{Kle09,
  title =     {The Normalized Compression Distance as a Distance
               Measure in Entity Identification},
  author =    {Klenk, S. and Thom, D. and Heidemann, G.},
  journal =   {Advances in Data Mining. Applications and Theoretical
               Aspects},
  publisher = {Springer},
  pages =     {325--337},
  year =      2009
}

@article{Kol11,
  author =    {Kolb, L. and Thor, A. and Rahm, E.},
  title =     {Multi-pass sorted neighborhood blocking with
               {Map-Reduce}},
  journal =   {Computer Science-Research and Development},
  publisher = {Springer},
  pages =     {1--19},
  year =      2011
}

@article{Kop10,
  author =    {K{\"o}pcke, H. and Rahm, E.},
  title =     {Frameworks for entity matching: A comparison},
  journal =   {Data and Knowledge Engineering},
  publisher = {Elsevier},
  volume =    69,
  number =    2,
  pages =     {197--210},
  year =      2010
}

@article{Kop10b,
  title =   {Evaluation of entity resolution approaches on
             real-world match problems},
  author =  {K{\"o}pcke, H. and Thor, A. and Rahm, E.},
  journal = {Proceedings of the VLDB Endowment},
  volume =  3,
  number =  {1-2},
  pages =   {484--493},
  year =    2010
}

@inproceedings{Kou04,
  author =    {Nick Koudas and Amit Marathe and Divesh Srivastava},
  title =     {Flexible string matching against large databases in
               practice},
  booktitle = {VLDB},
  address =   {Toronto},
  pages =     {1086--1094},
  year =      2004
}

@inproceedings{Kra97,
  title =     {{HMAC}: Keyed-hashing for message authentication},
  author =    {Krawczyk, H. and Bellare, M. and Canetti, R.},
  booktitle = {Internet RFCs},
  year =      1997
}

@book{Kro09,
  author =    {Krouse, W.J. and Elias, B.},
  title =     {Terrorist Watchlist Checks and Air Passenger
               Prescreening},
  publisher = {Congressional Research Service},
  note =      {CRS Report for Congress},
  number =    {RL33645},
  year =      2009
}

@inproceedings{Kro15,
  title =     {Who Is 1011011111...1110110010? {Automated}
               Cryptanalysis of {Bloom} Filter Encryptions of
               Databases with Several Personal Identifiers},
  author =    {Kroll, Martin and Steinmetzer, Simone},
  booktitle = {BIOSTEC},
  address =   {Lisbon},
  year =      2015
}
%% booktitle = {International Joint Conference on Biomedical
%% Engineering Systems and Technologies},
%%  pages =     {341--356},
  
@article{Kuk92,
  author =  {Kukich, Karen},
  title =   {Techniques for automatically correcting words in text},
  journal = {ACM Computing Surveys},
  volume =  24,
  number =  4,
  pages =   {377--439},
  year =    1992
}

@book{Kum03,
  author =    {Grama, Ananth and Karypis, George and Kumar, Vipin
               and Gupta, Anshul},
  title =     {Introduction to parallel computing},
  edition =   2,
  publisher = {Addison-Wesley Longman Publishing Co., Inc.},
  year =      2003
}

@article{Kum14,
  title =   {Social Genome: Putting Big Data to Work for Population
             Informatics},
  author =  {Hye-Chung Kum and Ashok Krishnamurthy and Ashwin
             Machanavajjhala and Stanley C. Ahalt},
  journal = {IEEE Computer},
  volume =  47,
  number =  1,
  year =    2014
}

@inproceedings{Kuz11,
  title =        {A Constraint Satisfaction Cryptanalysis of
                  {Bloom} Filters in Private Record Linkage},
  author =       {Kuzu, M. and Kantarcioglu, M. and Durham,
                  E. and Malin, B.},
  booktitle =    {PET},
  address =      {Waterloo},
  year =         2011
}
%%  booktitle =    {Privacy Enhancing Technologies},
%%  organization = {Springer},
%%  pages =        {226--245},
  
@article{Kuz13,
  author  = {Kuzu, M. and Kantarcioglu, M. and Durham, E. and
             Toth, C. and Malin, B.},
  title   = {A practical approach to achieve private medical
             record linkage in light of public resources},
  journal = {JAMIA},
  year    = 2013
}
%%  volume  = 20,
%%  number  = 2,
%%  pages   = {285--292},
  
@article{Lah05,
  author =    {Lahiri, P. and Larsen, M.D.},
  title =     {Regression analysis with linked data},
  journal =   {Journal of the American statistical association},
  publisher = {ASA},
  volume =    100,
  number =    469,
  pages =     {222--230},
  year =      2005
}

@techreport{Lai93,
  author =      {Lait, A.J. and Randell, B.},
  title =       {An Assessment of Name Matching Algorithms},
  institution = {Department of Computer Science},
  address =     {University of Newcastle upon Tyne},
  year =        1993
}

@inproceedings{Lai06,
  title =     {An Efficient {Bloom} Filter Based Solution for
               Multiparty Private Matching},
  author =    {Lai, P.K.Y. and Yiu, SM and Chow, KP and Chong, CF
               and Hui, L.C.K.},
  booktitle = {International Conference on Security and Management},
  pages =     7,
  year =      2006
}

@article{Law99,
  author =  {Lawrence, S. and Giles, C. Lee and Bollacker, K.},
  title =   {Digital libraries and autonomous citation indexing},
  journal = {IEEE Computer},
  volume =  32,
  number =  6,
  pages =   {67--71},
  year =    1999
}

@book{Lee06,
  author =    {Lee, Y.W. and Pipino, L.L. and Funk, J.D. and Wang,
               R.Y.},
  title =     {Journey to data quality},
  publisher = {The MIT Press},
  year =      2009
}

@article{Lee07,
  author =    {Lee, Dongwon and Kang, Jaewoo and Mitra, Prasenjit and
               Giles, C. Lee and On, Byung-Won},
  title =     {Are your citations clean?},
  journal =   {Commununications of the ACM},
  publisher = {ACM},
  volume =    50,
  issue =     12,
  pages =     {33--38},
 year =       2007
} 

@inproceedings{Len02,
  author =    {Lenzerini, M.},
  title =     {Data integration: A theoretical perspective},
  booktitle = {ACM SIGMOD-SIGACT-SIGART symposium on Principles
               of database systems},
  pages =     {233--246},
  address =   {Madison},
  year =      2002
}

@article{Li92,
  author =  {Li, Wentian},
  title =   {Random texts exhibit {Z}ipf's-law-like word frequency
             distribution},
  journal = {IEEE Transactions on Information Theory},
  volume =  38,
  number =  6,
  pages =   {1842--1845},
  year =    1992
}

@article{Li11b,
  author =  {Li, Pei and Dong, Xin L. and Maurino, Andrea and
             Srivastava, Divesh},
  title =   {Linking temporal records},
  journal = {PVLDB},
  volume =  4,
  number =  11,
  year =    2011
}

@inproceedings{Li11,
  title =     {Privacy preserving group linkage},
  author =    {Li, Fengjun and Chen, Yuxin and Luo, Bo and Lee,
               Dongwon and Liu, Peng},
  booktitle = {SSDBM, Springer LNCS},
  volume =     6809,
  address =   {Portland},
  pages =     {432--450},
  year =      2011
}


@article{Lin09,
  author =  {Lindell, Y. and Pinkas, B.},
  title =   {Secure multiparty computation for privacy-preserving
             data mining},
  journal = {Journal of Privacy and Confidentiality},
  volume =  1,
  number =  1,
  pages =   5,
  year =    2009
}

@inproceedings{Mal00,
  author =    {Jonathan I. Maletic and Andrian Marcus},
  title =     {Data cleansing: beyond integrity analysis},
  booktitle = {IQ},
  address =   {Boston},
  pages =     {200--209},
  year =      2000
}

@article{Mal05,
  author =  {Malin, B. and Airoldi, E. and Carley, K.M.},
  title =   {A network analysis model for disambiguation of names
             in lists},
  journal = {Computational and Mathematical Organization Theory},
  publisher={Springer},
  volume =  11,
  number =  2,
  pages =   {119--139},
  year =    2005
}

@article{Mal08,
  author =    {Malin, B.},
  title =     {K-Unlinkability: A privacy protection model for
               distributed data},
  journal =   {Data and Knowledge Engineering},
  publisher = {Elsevier},
  volume =    64,
  number =    1,
  pages =     {294--311},
  year =      2008
}

@article{Mal10,
  author =  {Malin, B. and Karp, D. and Scheuermann, R.H.},
  title =   {Technical and policy approaches to balancing patient
             privacy and data sharing in clinical and translational
             research},
  journal = {Journal of investigative medicine: the official
             publication of the American Federation for Clinical
             Research},
  volume =   58,
  number =   1,
  pages =    11,
  year =     2010
}

@article{Man11,
  title =     {{PACE}: A General-Purpose Tool for Authority Control},
  author =    {Manghi, P. and Mikulicic, M.},
  journal =   {Metadata and Semantic Research},
  publisher = {Springer},
  pages =     {80--92},
  year =      2011
}

@Misc{Mat98,
  title =  {{AutoStan and AutoMatch, User's Manuals}},
  author = {MatchWare Technologies},
  note =   {Kennebunk, Maine},
  year =   1998
}

@inproceedings{Mcc00a,
  author =    {Andrew McCallum and Kamal Nigam and Lyle H. Ungar},
  title =     {Efficient Clustering of High-Dimensional Data Sets with
               Application to Reference Matching},
  booktitle = {ACM SIGKDD},
  address =   {Boston},
  pages =     {169--178},
  year =      2000
}

@article{Mcc00b,
  author =   {Andrew McCallum and Kamal Nigam and Rennie, J. and
              Seymore, K.},
  title=     {Automating the construction of {Internet} portals with
              machine learning},
  journal =  {Information Retrieval},
  publisher= {Springer},
  volume =   3,
  number =   2,
  pages =    {127--163},
  year =     2000
}

@inproceedings{Men06,
  title =     {Generic entity resolution with data confidences},
  author =    {Menestrina, D. and Benjelloun, O. and
               Garcia-Molina, H.},
  booktitle = {First International VLDB Workshop on Clean Databases},
  address =   {Seoul, South Korea},
  year =      2006
}

@article{Men10,
  author =  {Menestrina, D. and Whang, S.E. and Garcia-Molina, H.},
  title =   {Evaluating entity resolution results},
  journal = {Proceedings of the VLDB Endowment},
  volume =  3,
  number =  {1--2},
  pages =   {208--219},
  year =    2010,
}

@inproceedings{Mic06,
  author =    {Matthew Michelson and Craig A. Knoblock},
  title =     {Learning Blocking Schemes for Record Linkage},
  booktitle = {AAAI},
  address=    {Boston},
  year =      2006
}

@book{Mit97,
  author =    {Mitchell, Ton M.},
  title =     {Machine Learning},
  publisher = {McGraw Hill},
  year =      1997
}

@inproceedings{Mon96,
  author =    {Monge, Alvaro E. and Elkan, Charles P.},
  title =     {The field-matching problem: Algorithm and
               applications},
  booktitle = {ACM SIGKDD},
  address =   {Portland},
  pages =     {267--270},
  year =      1996
}

@article{Mon00,
  author =  {Monge,  Alvaro E.},
  title =   {Matching algorithms within a duplicate detection system},
  journal = {IEEE Data Engineering Bulletin},
  volume =  23,
  number =  4,
  pages =   {14--20},
  year =    2000
}

@inproceedings{Mor08,
  title =       {Robust similarity measures for named entities
                 matching},
  author =      {Moreau, E. and Yvon, F. and Capp{\'e}, O.},
  booktitle =   {22nd International Conference on Computational
                 Linguistics-Volume 1},
  organization= {Association for Computational Linguistics},
  pages =       {593--600},
  year =        2008
}

@article{Mou09,
  author =    {Moustakides, George V. and Verykios, Vassilios S.},
  title =     {Optimal Stopping: A Record Linkage Approach},
  journal =   {Journal Data and Information Quality},
  publisher = {ACM},
  volume =    1,
  issue =     2,
  pages =     {9:1--9:34},
  year =      2009
}

@article{Nar10,
  title =   {Myths and fallacies of personally identifiable
             information},
  author=   {Narayanan, A. and Shmatikov, V.},
  journal = {Communications of the ACM},
  volume =  53,
  number =  6,
  pages =   {24--26},
  year =    2010
}

@book{Nau10,
  title =     {An introduction to duplicate detection},
  author =    {Naumann, Felix and Herschel, Melanie},
  publisher = {Morgan and Claypool Publishers},
  series =    {Synthesis Lectures on Data Management},
  year =      2010
}
%%  volume =    3,


@article{Nav01,
  author =  {Navarro, Gonzalo},
  title =   {A guided tour to approximate string matching},
  journal = {ACM Computing Surveys},
  volume =  33,
  number =  1,
  pages =   {31--88},
  year =    2001
}

@article{New59,
  title =   {Automatic linkage of vital records},
  author =  {Newcombe, H.B. and Kennedy, J.M. and Axford, SJ and
             James, AP},
  journal = {Science},
  volume =  130,
  number =  3381,
  pages =   {954--959},
  year =    1959
}

@article{New62,
  author =    {Newcombe, Howard B. and Kennedy, James M.},
  title =     {Record linkage: making maximum use of the
               discriminating power of identifying information},
  journal =   {Communications of the ACM},
  volume =    5,
  number =    11,
  pages =     {563--566},
  issn =      {0001-0782},
  publisher = {ACM},
  year =      1962
}

@book{New88,
 author =    {Newcombe, Howard B.},
 title =     {Handbook of record linkage: methods for health and
              statistical studies, administration, and business},
 isbn =      {0-19-261732-X},
 publisher = {Oxford University Press, Inc.},
 address =   {New York, NY, USA},
 year =      1988
}

@techreport{New13,
  title =       {Family reconstitution in an urban context: some
                 observations and methods},
  author =      {Newton, Gill},
  institution = {University of Cambridge},
  note =        {CWPESH no.\ 12},
  year =        2013
}

@article{Nie14,
  author =    {Niedermeyer, Frank and Steinmetzer, Simone and
               Kroll, Martin and Schnell, Rainer},
  title =     {Cryptanalysis of Basic {Bloom} Filters Used for
               Privacy Preserving Record Linkage},
  journal =   {JPC},
  volume =    6,
  number =    2,
  pages =     {59--79},
  year =      2014
}
%%  journal =   {Journal of Privacy and Confidentiality},
  
@inproceedings{Nin07,
  author =    {Jordi Nin and Victor Muntes-Mulero and Norbert
               Martinez-Bazan and Joseph-L. Larriba-Pey},
  title =     {On the Use of Semantic Blocking Techniques for Data
              Cleansing and Integration},
  booktitle = {IDEAS},
  address =   {Banff, Canada},
  pages =     {190--198},
  year = 2007
}

@article{Ode18,
  author =  {Odell, M. and Russell, RC},
  title =   {The soundex coding system},
  journal = {US Patents},
  volume =  {1261167},
  year =    1918
}

@inproceedings{Oke04,
  title =     {Privacy-preserving data linkage protocols},
  author =    {O'Keefe, C.M. and Yung, M. and Gu, L. and Baxter, R.},
  booktitle = {ACM Workshop on Privacy in the Electronic Society},
  address =   {Washington DC},
  pages =     {94--102},
  year =      2004
}

@article{Okn74,
  author =    {Okner, B.},
  title =     {Data Matching and Merging: An Overview},
  journal =   {NBER Chapters},
  pages =     {49--54},
  publisher = {National Bureau of Economic Research, Inc},
  year =      1974
}

@inproceedings{On06,
  author =    {Byung-Won On and Ergin Elmacioglu and Dongwon Lee
               and Jaewoo Kang and Jian Pei},
  title =     {Improving Grouped-Entity Resolution Using
               Quasi-Cliques},
  booktitle = {IEEE ICDM},
  location =  {Hong Kong},
  year =      2006
}
%%  pages =     {1008--1015},


@inproceedings{On07,
  author =    {Byung-Won On and Nick Koudas and Dongwon Lee and Divesh
               Srivastava},
  title =     {Group Linkage},
  booktitle = {IEEE ICDE},
  address =   {Istanbul},
  year =      2007
}
%%  pages =     {496--505},


@misc{ONS13,
  title =  {Beyond 2011 Matching Anonymous Data},
  note =   {Methods and Policies Report M9},
  author = {{Office for National Statistics}},
  year =   2013
}

@article{Osc05,
  author =  {Oscherwitz, T.},
  title =   {Synthetic identity fraud: unseen identity challenge},
  journal = {Bank Security News},
  volume =  3,
  number =  7,
  year =    2005
}

@article{Pan09,
  author =    {Chaoyi Pang and Lifang Gu and David Hansen and Anthony Maeder},
  title =     {Privacy-Preserving Fuzzy Matching Using a Public
               Reference Table},
  journal =   {Intelligent Patient Management},
  publisher = {Springer},
  pages =     {71--89},
  year =      2009
}

@article{Pap13,
  title =   {A blocking framework for entity resolution in highly
             heterogeneous information spaces},
  author =  {Papadakis, George and Ioannou, Ekaterini and Palpanas,
             Themis and Niederee, Claudia and Nejdl, Wolfgang},
  journal = {IEEE TKDE},
  volume =  25,
  number =  12,
  pages =   {2665--2682},
  year =    2013
}

@article{Pap16,
  title =   {Comparative analysis of approximate blocking
             techniques for entity resolution},
  author =  {Papadakis, George and Svirsky, Jonathan and
             Gal, Avigdor and Palpanas, Themis},
  journal = {PVLDB},
  volume =  9,
  number =  9,
  pages =   {684--695},
  year =    2016
}

@inproceedings{Pat03,
  author =    {Patman, Frankie and Thompson, Paul},
  title =     {Names: A New Frontier in Text Mining},
  booktitle = {ISI-2003, Springer LNCS 2665},
  pages =     {27--38},
  year =      2003
}

@misc{Pau03,
  author =       {Paull, D.L.},
  title = 	 {A geocoded national address file for {A}ustralia:
                  {T}he {G-NAF} What, Why, Who and When?},
  howpublished = {PSMA Australia Limited, Griffith, ACT, Australia},
  year =         2003
}
%  note =         {Available at: \texttt{http://www.g-naf.com.au/}},

@article{Pfe96,
  author =  {Pfeifer, Ulrich and Poersch, Thomas and Fuhr, Norbert},
  title =   {Retrieval effectiveness of proper name search methods},
  journal = {Information Processing and Management},
  volume =  32,
  number =  6,
  pages =   {667--679},
  year =    1996
}

@article{Phi00,
  author =  {Philips, Lawrence},
  title =   {The Double-Metaphone Search Algorithm},
  journal = {C/C++ User's Journal},
  volume =  18,
  number =  6,
  year =    2000
}

@article{Phu12,
  title =   {Resilient Identity Crime Detection},
  author =  {Phua, C. and Smith-Miles, K. and Lee, V. and Gayler, R.},
  journal = {IEEE Transactions on Knowledge and Data Engineering},
  volume =  24,
  number =  3,
  year =    2012
}

@inproceedings{Poi03,
  author =    {Poindexter, J. and Popp, R. and Sharkey, B.},
  title =     {Total information awareness {(TIA)}},
  booktitle = {IEEE Aerospace Conference, 2003},
  volume =    6,
  pages =     {2937--2944},
  year =      2003
}

@article{Pol84,
  author =  {Pollock, Joseph J. and Zamora, Antonio},
  title =   {Automatic spelling correction in scientific and scholarly
             text},
  journal = {Communications of the ACM},
  volume =  27,
  number =  4,
  pages =   {358--368},
  year =    1984
}

@techreport{Por97,
  author =      {Porter, Edward H. and Winkler, William E.},
  title =       {Approximate string comparison and its effect on an
                 advanced record linkage system},
  number =      {RR97/02},
  institution = {US Bureau of the Census},
  year =        1997,
}

@inproceedings{Pra09,
  author =    {Prabhakar, S. and Shah, R. and Singh, S.},
  title =     {Indexing Uncertain Data},
  booktitle = {Managing and Mining Uncertain Data},
  editor =    {Charu C. Aggarwal},
  series =    {Advances in Database Systems},
  publisher = {Springer},
  pages =     {299--325},
  volume =    35,
  year =      2009
}

@inproceedings{Pra11,
  author =    {Prasad, K.H. and Faruquie, T.A. and Joshi, S. and
               Chaturvedi, S. and Subramaniam, L.V. and Mohania, M.},
  title =     {Data Cleansing Techniques for Large Enterprise
               Datasets},
  booktitle = {SRII Global Conference},
  address =   {San Jose, USA},
  pages=      {135--144},
  year =      2009
}

@book{Pyl99,
  author =    {Pyle, Dorian},
  title =     {Data preparation for data mining},
  publisher = {Morgan Kaufmann},
  year =      1999
}

@article{Qua96,
  author =    {Quantin, Catherine and Bouzelat, Hocine and Dusserre,
               Liliane},
  title =     {Irreversible encryption method by generation of
               polynomials},
  journal =   {Medical Informatics and the Internet in Medicine},
  publisher = {Informa Healthcare},
  volume =    21,
  number =    2,
  year=       1996
}
%%  pages =     {113--121},


@Article{Qua98,
  author =  {Quantin, Catherine and Bouzelat, H. and Allaert, F.A.A.
             and Benhamiche, A.M. and Faivre, J. and Dusserre, L.},
  title =   {How to Ensure Data Quality of an Epidemiological
             Follow-up: Quality Assessment of an Anonymous Record
             Linkage Procedure},
  journal = {International Journal of Medical Informatics},
  volume =  49,
  number =  1,
  pages =   {117-122},
  year =    1998
}

@article{Qua98b,
  author =    {Quantin, Catherine and Bouzelat, Hocine and Allaert,
               Francois-Andre and Benhamiche, Anne-Marie and Faivre,
               Jean and Dusserre, Liliane},
  title =     {Automatic record hash coding and linkage for
               epidemiological follow-up data confidentiality},
  journal =   {Methods of Information in Medicine},
  publisher = {Schattauer},
  volume =    37,
  number =    3,
  pages =     {271--277},
  year=       1998
}

@inproceedings{Qua03,
  author =    {Quass, Dallan and Starkey, Paul},
  title =     {Record linkage for genealogical databases},
  booktitle = {ACM SIGKDD Workshop on Data Cleaning, Record Linkage
               and Object Consolidation},
  address =   {Washington DC},
  pages =     {40--42},
  year =      2003
}

@article{Rab89,
  author =  {Rabiner, L.R.},
  title =   {A tutorial on hidden {Markov} models and selected
             applications in speech recognition},
  journal = {Proceedings of the IEEE},
  volume =  77,
  number =  2,
  pages =   {257--286},
  year =    1989
}

@article{Rah00,
  author =  {Erhard Rahm and Hong Hai Do},
  title =   {Data Cleaning: Problems and Current Approaches},
  journal = {IEEE Data Engineering Bulletin},
  volume =  23,
  number =  4,
  pages =   {3--13},
  year =    2000
}

@inproceedings{Ram13,
  title =     {Dynamic Similarity-Aware Inverted Indexing for
               Real-Time Entity Resolution},
  author =    {Ramadan, Banda and Christen, Peter and Liang,
               Huizhi and Gayler, Ross W. and Hawking, David},
  booktitle = {PAKDD Workshops},
  address =   {Gold Coast, Australia},
  year =      2013
}
%  booktitle = {PAKDD Workshops, Springer LNAI},
%  volume =     7867,
%  address =   {Gold Coast, Australia},
%  pages =     {47--58},

@inproceedings{Ram14,
  title =     {Dynamic Sorted Neighborhood Indexing for Real-Time
               Entity Resolution},
  author =    {Ramadan, Banda and Christen, Peter and Liang,
               Huizhi},
  booktitle = {ADC, Springer LNCS},
  volume =    8506,
  address =   {Brisbane},
  pages =     {1--12},
  year = 2014
}

@inproceedings{Ram15,
  title =     {Unsupervised blocking key selection for real-time
               entity resolution},
  author =    {Ramadan, Banda and Christen, Peter},
  booktitle = {PAKDD},
  address =   {Ho Chi Minh City},
  year =      2015
}
%%  pages={574--585},
%%  organization={Springer}  

@article{Ran14,
  title =     {Privacy-preserving record linkage on large real
               world datasets},
  author =    {Randall, Sean and Ferrante, Anna and Boyd, James
               and Bauer, Jacqueline and Semmens, James},
  journal =   {JBI},
  publisher = {Academic Press},
  volume =    50,
  pages =     {205--212},
  year =      2014
}
%%  author =    {Randall, Sean M and Ferrante, Anna M and Boyd,
%%               James H and Bauer, Jacqueline K and Semmens,
%                James B},
%%  journal =   {Journal of biomedical informatics},
  
@inproceedings{Ran14b,
  author =   {Ranbaduge, Thilina and Christen, Peter and
              Vatsalan, Dinusha},
  title =    {Tree Based Scalable Indexing for Multi-Party
              Privacy-Preserving Record Linkage},
  booktitle = {AusDM, CRPIT},
  volume =    158,
  address =   {Brisbane, Australia},
  year =      2014
}

@inproceedings{Ran15,
 address              = {Hanoi},
 author               = {Ranbaduge, Thilina and Christen, Peter and Vatsalan, Dinusha},
 booktitle            = {PAKDD, Springer LNAI},
 title                = {Clustering-based Scalable Indexing for Multi-party Privacy-preserving Record Linkage},
 year                 = {2015},
 }


@inproceedings{Ran16,
  title =     {Hashing-Based Distributed Multi-party Blocking for
               Privacy-Preserving Record Linkage},
  author =    {Ranbaduge, Thilina and Vatsalan, Dinusha and Christen,
               Peter and Verykios, Vassilios},
  booktitle = {PAKDD},
  year =      2016
}
%%  address =   {Auckland},
%%  pages =     {415--427},

@article{Ras11,
 author =  {Rastogi, Vibhor and Dalvi, Nilesh and Garofalakis, Minos},
 title =   {Large-scale collective entity matching},
 journal = {VLDB Endowment},
 volume =  4,
 issue =   4,
 pages =   {208--218},
 year =    2011
}

@inproceedings{Rav04,
  title =     {A secure protocol for computing string distance
               metrics},
  author =    {Ravikumar, P. and Cohen, W.W. and Fienberg, S.E.},
  booktitle = {Workshop on Privacy and Security Aspects of Data
               Mining held at IEEE ICDM},
  address =   {Brighton, UK},
  pages=      {40--46},
  year =      2004
}

@misc{Riv98,
  author =       {Rivest, Ronald L.},
  title =        {Chaffing and Winnowing: Confidentiality without
                  Encryption},
  howpublished = {MIT Lab for Computer Science},
  note =         {Available at: \\
        \texttt{http://theory.lcs.mit.edu/$\sim$rivest/chaffing.txt}},
  year = 1998
}

@article{Rud13,
  title =     {Machine learning for science and society},
  author =    {Rudin, Cynthia and Wagstaff, Kiri L},
  journal =   {Machine Learning},
  publisher = {Springer},
  year =      2013
}
%%  pages =     {1--9},

@article{Rug02,
  author =    {Ruggles, Steven},
  title =     {Linking historical censuses: A new approach},
  journal =   {History and Computing},
  publisher = {Edinburgh University Press},
  volume =    14,
  number =    {1--2},
  pages =     {213--224},
  year =      2002
}

@article{Rus06,
  author =  {Rushton, G. and Armstrong, M.P. and Gittler, J.
             and Greene, B.R. and Pavlik, C.E. and West, M.M.
             and Zimmerman, D.L.},
  title =   {Geocoding in Cancer Research: A Review},
  journal = {American Journal of Preventive Medicine},
  volume =  30,
  number =  2,
  pages =   {S16--S24},
  year =    2006
}

@article{Sad11,
  author =  {Sadinle, M. and Hall, R. and Fienberg, S.E.},
  title =   {Approaches to Multiple Record Linkage},
  journal = {Proceedings of International Statistical Institute},
  address = {Dublin, Ireland},
  year =    2011
}

@inproceedings{Sar02,
  author =    {Sarawagi, S. and Bhamidipaty, A.},
  title =     {Interactive deduplication using active learning},
  booktitle = {ACM SIGKDD},
  address =   {Edmonton},
  pages =     {269--278},
  year =      2002
}

@inproceedings{Sar04,
  author =    {Sarawagi, S. and Kirpal, A.},
  title =     {Efficient set joins on similarity predicates},
  booktitle = {ACM SIGMOD},
  pages =     {754--765},
  address =   {Paris},
  year =      2004
}

@article{Sar08,
  title =     {Information extraction},
  author =    {Sarawagi, S.},
  journal =   {Foundations and Trends in Databases},
  publisher = {Now Publishers Inc.},
  volume =    1,
  number =    3,
  pages =     {261--377},
  year =      2008
}

@article{Sar10,
  author =  {Sariyar, M. and Borg, A.},
  title =   {The {RecordLinkage} Package: Detecting Errors in Data},
  journal = {The R Journal},
  volume =  2,
  number =  2,
  pages =   {61--67},
  year = 2010
}

@inproceedings{Sca07,
  title =     {Privacy preserving schema and data matching},
  author =    {Monica Scannapieco and Ilya Figotin and Elisa Bertino
               and Ahmed K. Elmagarmid},
  booktitle = {ACM SIGMOD},
  address =   {Beijing},
  pages =     {653--664},
  year =      2007
}

@article{Sch93,
  author =    {Scheuren, F. and Winkler, W.E.},
  title =     {Regression analysis of data files that are computer
               matched},
  journal =   {Statistics of income: Turning administrative systems
               into information systems},
  publisher = {Statistics of Income Division, Internal Revenue
               Service},
  volume =   1299,
  number =   1,
  pages =    131,
  year =     1993
}

@inproceedings{Sch12,
  author =    {Schewe, K.D. and Wang, Q.},
  title =     {On the Decidability and Complexity of Identity
               Knowledge Representation},
  booktitle = {Database Systems for Advanced Applications,
               Springer LNCS 7238},
  address =   {Busan, South Korea},
  pages =     {288--302},
  year =      2012
}

@book{Sch96,
  author =    {Schneier, Bruce},
  title =     {Applied cryptography: Protocols, algorithms, and
               source code in C},
  edition =   2,
  publisher = {John Wiley and Sons, Inc.},
  address =   {New York},
  year =      1996
}

@article{Sch04,
  title =   {A Toolbox for record linkage},
  author =  {Schnell, R. and Bachteler,  T. and Bender, S.},
  journal = {Austrian Journal of Statistics},
  volume =  33,
  number =  {1 \& 2},
  pages =   {125--133},
  year =    2004
}

@article{Sch09,
  title =   {Privacy-preserving record linkage using {Bloom}
            filters},
  author =  {Rainer Schnell and Tobias Bachteler and J\"org
             Reiher},
  journal = {BMC Med Inform Decis Mak},
  volume =  9,
  number =  1,
  year =    2009
}
%%  journal = {BioMed Central Medical Informatics and Decision
%%             Making},

@article{Sch11,
  author =  {Schnell, Rainer and Bachteler, Tobias and Reiher,
             J{\"o}rg},
  journal = {working paper, German Record Linkage Center},
  title =   {A novel error-tolerant anonymous linking code},
  year =    2011
}
%%, working paper  WP-GRLC-2011-02},

@article{Sch14,
  title =   {An efficient privacy-preserving record linkage
            technique for administrative data and censuses},
  author =  {Rainer Schnell},
  journal = {SJIAOS},
  volume =  30,
  number =  3,
  pages  =  {263--270},
  year =    2014
}
%%  journal = {Statistical Journal of the IAOS},

@inproceedings{Sch15,
   author =    {Schnell, Rainer},
   booktitle = {Methodological Developments in Data Linkage},
   editor =    {Katie Harron and Harvey Goldstein and Chris Dibben},
   title =     {Privacy-Preserving Record Linkage},
   year =      2015
 }
%%   publisher = {John Wiley \& Sons},
%%   pages =     {201--225},
   
@inproceedings{Sch16,
  title =     {Randomized Response and Balanced {Bloom} Filters for
               Privacy Preserving Record Linkage},
  author =    {Rainer Schnell and Christian Borgs},
  booktitle = {ICDMW DINA},
  address =  {Barcelona},
  year=      2016
}

@article{Sch16b,
 author =  {Rainer Schnell and Christian Borgs},
 journal = {working paper, German Record Linkage Center},
 title =   {Identification of attribute fields in
            {Bloom}-filter based Record-Linkage},
 year =    2016
}

@inproceedings{Seh15,
  title =     {Privacy Preserving Record Linkage with {PPJoin}},
  author =    {Sehili, Ziad and Kolb, Lars and Borgs, Christian and
               Schnell, Rainer and Rahm, Erhard},
  booktitle = {BTW Conference},
  address =   {Hamburg},
  year=       2015
}

@inproceedings{Sey99,
  title =     {Learning hidden {Markov} model structure for
               information extraction},
  author =    {Seymore, K. and McCallum, A. and Rosenfeld, R.},
  booktitle = {AAAI Workshop on Machine Learning for Information
              Extraction},
  pages =     {37--42},
  year =      1999
}

@book{Sie13,
  title =     {Predictive Analytics: The Power to Predict who Will
               Click, Buy, Lie, Or Die},
  author =    {Siegel, Eric},
  publisher = {John Wiley and Sons},
  year =      2013
}

@article{Smi75,
  author =  {Smith, M.E. and Newcombe, H.B.},
  title =   {Methods for computer linkage of hospital
             admission-separation records into cumulative health
             histories.},
  journal = {Methods of Information in Medicine},
  volume =  14,
  number =  3,
  pages =   {118--125},
  year =    1975
}

@article{Smi79,
  title =   {Accuracies of computer versus manual linkages of routine
             health records},
  author =  {Smith, M.E. and Newcombe, H.B.},
  journal = {Methods of Information in Medicine},
  volume =  18,
  number =  2,
  pages =   {89--97},
  year =    1979
}

@article{Sna07,
  title =   {A comparison and analysis of name matching algorithms},
  author =  {Snae, C.},
  journal = {International Journal of Applied Science, Engineering
             and Technology},
  volume =  4,
  number =  1,
  pages =   {252--257},
  year =    2007
}

@inproceedings{Son00,
  title =     {Practical techniques for searches on encrypted data},
  author =    {Song, D.X. and Wagner, D. and Perrig, A.},
  booktitle = {IEEE Symposium on Security and Privacy},
  pages =     {44--55},
  year =      2000
}

@article{Su09,
  author =  {Weifeng Su and Jiying Wang and Frederick H. Lochovsky},
  title =   {Record Matching over Query Results from Multiple Web
             Databases},
  journal = {IEEE Transactions on Knowledge and Data Engineering},
  volume =  22,
  number =  4,
  pages =   {578--589},
  year =    2009
}

@article{Sum06,
  author =  {Summerhayes, R. and Holder, P. and Beard, J. and Morgan,
             G. and Christen, P. and Willmore, A. and Churches, T.},
  title =   {Automated geocoding of routinely collected health data
             in {New South Wales}},
  journal = {New South Wales Public Health Bulletin},
  publisher={CSIRO},
  volume =  17,
  number =  4,
  pages =   {33--38},
  year =    2006
}

@phdthesis{Swe01,
  author = {Sweeney, L.},
  title =  {Computational disclosure control: A primer on data
            privacy protection},
  school = {Massachusetts Institute of Technology, Dept. of
            Electrical Engineering and Computer Science},
  year =  2001
}

@article{Swe02,
  title =   {K-anonymity: A model for protecting privacy},
  author =  {Sweeney, L.},
  journal = {International Journal of Uncertainty Fuzziness and
             Knowledge Based Systems},
  volume =  10,
  number =  5,
  pages =   {557--570},
  year =    2002
}

@inproceedings{Tal09,
  title =     {{SOG}: A Synthetic Occupancy Generator to Support
               Entity Resolution Instruction and Research},
  author =    {John R. Talburt and Yinle Zhou and Savitha Yalanadu
               Shivaiah},
  booktitle = {International Conference on Information Quality},
  address =   {Potsdam, Germany},
  pages =     {91--105},
  year =      2009 
}

@book{Tal11,
  author =    {Talburt, John R.},
  title =     {Entity Resolution and Information Quality},
  isbn =      {978-0-12-381972-7},
  publisher = {Morgan Kaufmann},
  year =      2011
}

@inproceedings{Tej02,
  author =    {Tejada, S. and Knoblock, C. A. and Minton, S.},
  title =     {Learning domain-independent string transformation
               weights for high accuracy object identification},
  booktitle = {ACM SIGKDD},
  address =   {Edmonton},
  pages =     {350--359},
  year =      2002
}

@article{Tor03,
  author =   {Torra, V. and Domingo-Ferrer, J.},
  title =    {Record linkage methods for multidatabase data mining},
  journal =  {Studies in Fuzziness and Soft Computing},
  publisher= {Physica Verlag},
  volume =   123,
  pages =    {101--132},
  year =     2003
}

@inproceedings{Tor04,
  author =    {Torra, V. and Domingo-Ferrer, J. and Torres, A.},
  title=      {Data mining methods for linking data coming from
               several sources},
  booktitle = {Third Joint UN/ECE-Eurostat Work Session on
               Statistical Data Confidentiality, Eurostat.
               Monographs in Official Statistics},
  address =   {Luxembourg},
  year =      2004
}

@article{Tox14,
 author =  {Toxen, Bob},
 title =   {The {NSA} and {Snowden}: Securing the All-seeing Eye},
 journal = {Communications of the ACM},
 volume =  57,
 number =  5,
 pages =   {44--51},
 year =    2014
}

@article{Tre08,
  title  =    {Privacy-preserving string comparisons in record
               linkage systems: a review},
  author =    {Trepetin, Stanley},
  journal =   {Information Security Journal: A Global Perspective},
  publisher = {Taylor and Francis},
  volume =    17,
  number =    5,
  pages =     {253--266},
  year =      2008
}

@article{USF03,
  author =  {{US Federal Geographic Data Committee. Homeland
             Security and Geographic Information Systems}},
  title =   {How {GIS} and mapping technology can save lives and
             protect property in post-{September} 11th {America}},
  journal = {Public Health GIS News and Information},
  number =  52,
  pages =   {21--23},
  month =   {May},
  year =    2003
}

@book{Vai06,
  title =     {Privacy preserving data mining},
  author =    {Vaidya, J. and Clifton, C.W. and Zhu, M.},
  publisher = {Springer},
  volume =    19,
  year =      2006
}

@article{Van00,
  title =     {Evaluation of the encryption procedure and record
               linkage in the {Belgian National Cancer Registry}},
  author =    {Van Eycken, E. and Haustermans, K. and Buntinx, F.
               and Ceuppens, A. and Weyler, J. and Wauters, E. and
               Van, O.},
  journal =   {Archives of Public Health},
  publisher = {Archives {Belges} de medecine sociale},
  volume =    58,
  number =    6,
  pages =     {281--294},
  year =      2000
}

@book{Vap00,
  author =    {Vapnik, V.N.},
  title =     {The nature of statistical learning theory},
  publisher = {Springer},
  year =      2000
}

@inproceedings{Vat11,
  author =    {Dinusha Vatsalan and Peter Christen and Vassilios
               Verykios},
  title =     {An Efficient Two-Party Protocol for Approximate
               Matching in Private Record Linkage},
  booktitle = {AusDM, CRPIT},
  volume =    121,
  address =   {Ballarat, Australia},
  year =      2011
}

@inproceedings{Vat12,
  author =   {Vatsalan, Dinusha and Christen, Peter},
  title =    {An Iterative Two-party Protocol for Scalable 
              Privacy-Preserving Record Linkage},
  booktitle = {AusDM, CRPIT},
  volume =    134,
  address =   {Sydney, Australia},
  year =      2012
}

@article{Vat13,
  author =   {Vatsalan, Dinusha and Christen, Peter and Verykios,
              Vassilios},
  title =    {A Taxonomy of Privacy-Preserving Record Linkage
              Techniques},
  journal =  {Elsevier IS},
  volume =   38,
  number =   6,
  pages =    {946--969},
  year =     2013
}
  journal =  {Information Systems},
  publisher= {Elsevier},
  
@inproceedings{Vat13b,
 author =    {Vatsalan, Dinusha and Christen, Peter and
              Verykios, Vassilios S.},
 title =     {Efficient Two-party Private Blocking Based on
              Sorted Nearest Neighborhood Clustering},
 booktitle = {ACM CIKM},
 address =   {San Francisco},
 pages =     {1949--1958},
 year =      2013
}

@inproceedings{Vat13c,
  title =     {Sorted nearest neighborhood clustering for efficient
               private blocking},
  author =    {Vatsalan, Dinusha and Christen, Peter},
  booktitle = {PAKDD},
  address =   {Gold Coast, Australia},
  pages =     {341--352},
  year =      2013
}

@article{Vat14,
  title =   {An Evaluation Framework for Privacy-Preserving Record
             Linkage},
  author =  {Vatsalan, Dinusha and Christen, Peter and O'Keefe,
             Christine M and Verykios, Vassilios},
  journal = {JPC},
  volume =  6,
  number =  1,
  year =    2014
}
%%  journal = {Journal of Privacy and Confidentiality},
  
@phdthesis{Vat14b,
 author               = {Vatsalan, Dinusha},
 school               = {Research School of Computer Science, The Australian National University},
 title                = {Scalable and approximate privacy-preserving record linkage},
 year                 = {2014},
 }

@inproceedings{Vat14c,
 address              = {Shanghai},
 author               = {Vatsalan, Dinusha and Christen, Peter},
 booktitle            = {ACM CIKM},
 title                = {Scalable Privacy-Preserving Record Linkage
                        for Multiple Databases},
 year                 = 2014
 }

@article{Vat16,
  title =   {Privacy-preserving matching of similar patients},
  author =  {Vatsalan, Dinusha and Christen, Peter},
  journal = {JBI},
  publisher={Academic Press},
  volume =  59,
  pages =   {285--298},
  year =    2016
}
%%  journal = {Journal of Biomedical Informatics},

@inproceedings{Vat16b,
 address              = {Barcelona, Spain},
 author               = {Vatsalan, Dinusha and Christen, Peter and Rahm, Erhard},
 booktitle            = {IEEE ICDMW},
 title                = {Scalable Privacy-Preserving Linking of Multiple Databases using Counting Bloom Filters},
 year                 = {2016},
 }

@inproceedings{VBe88,
  author =    {Van Berkel, Brigitte and De Smedt, Koenraad},
  title =     {Triphone analysis: A combined method for the correction
               of orthographical and typographical errors},
  booktitle = {Second Conference on Applied Natural Language
               Processing},
  address =   {Austin},
  pages =     {77--83},
  year =      1988
}

@article{Ver00,
  author =    {Verykios, V.S. and Elmagarmid, A.K. and Houstis, E.N.},
  title =     {Automating the approximate record-matching process},
  journal =   {Information Sciences},
  publisher = {Elsevier},
  volume =    126,
  number =    {1--4},
  pages =     {83--98},
  year =      2000
}

@article{Ver03,
  author =  {Vassilios S. Verykios and Moustakides V.
             George and Mohamed G. Elfeky},
  title =   {A {Bayesian} decision model for cost optimal record
             matching},
  journal = {The VLDB Journal},
  publisher={Springer},
  volume =  12,
  number =  1,
  pages =   {28--40},
  year =    2003
}

@article{Ver09,
  author =    {Verykios, Vassilios S. and Karakasidis, Alexandros
               and Mitrogiannis,  Vassilios K.},
  title =     {Privacy preserving record linkage approaches},
  journal =   {Int.\ J.\ of Data Mining, Modelling and
               Management},
  publisher = {Inderscience},
  volume =    1,
  number =    2,
  pages =     {206--221},
  year =      2009
}

@article {Ver13,
author =  {Verykios, Vassilios S. and Christen, Peter},
title =   {Privacy-preserving record linkage},
journal = {Wiley Interdisciplinary Reviews: Data Mining and
           Knowledge Discovery},
volume =  3,
number =  5,
pages =   {321--332},
year =    2013
}

@inproceedings{Vol09,
  author =    {Volz, J. and Bizer, C. and Gaedke, M. and
               Kobilarov, G.},
  title =     {Silk--a link discovery framework for the web of data},
  booktitle = {Second Linked Data on the Web Workshop},
  year =      2009
}

@article{Wan04,
  title =   {Automatically detecting deceptive criminal identities},
  author =  {Wang, G. and Chen, H. and Atabakhsh, H.},
  journal = {Communications of the ACM},
  volume =  47,
  number =  3,
  pages =   {70--76},
  year =    2004
}

@inproceedings{Wan15,
  title =      {Efficient interactive training selection for
                large-scale entity resolution},
  author =    {Wang, Qing and Vatsalan, Dinusha and Christen, Peter},
  booktitle = {PAKDD},
  address =   {Ho Chi Minh City},
  year =     2015
}
%%  pages={562--573},
%%  organization={Springer}  

@misc{War01,
  author = 	 {Wartell, Julie and McEwen, Thomas},
  title = 	 {Privacy in the Information Age: A Guide for Sharing
                  Crime Maps and Spatial Data},
  howpublished = {Institute for Law and Justice, NCJ 188739},
  month = 	 {July},
  year = 	 2001
}

@inproceedings{Wha09,
  author =    {Whang, Steven Euijong and Menestrina, David and
               Koutrika, Georgia and Theobald, Martin and
               Garcia-Molina, Hector},
  title =     {Entity resolution with iterative blocking},
  booktitle = {ACM SIGMOD},
  address =   {Providence, Rhode Island},
  pages =     {219--232},
  year =      2009
}

@article{Wha10,
  author =    {Whang, S.E. and Garcia-Molina, H.},
  title =     {Entity resolution with evolving rules},
  journal =   {Proceedings of the VLDB Endowment},
  publisher = {VLDB Endowment},
  volume =    3,
  number =    {1-2},
  pages =     {1326--1337},
  year =      2010
}

@techreport{Wha11,
  author =      {Whang, Steven Euijong and Garcia-Molina, Hector},
  title =       {A Model for Quantifying Information Leakage},
  publisher =   {Stanford InfoLab},
  institution = {Stanford University},
  number =      {1007},
  year = 2011
}

@techreport{Wha11b,
  author =      {Steven Euijong Whang and Hector Garcia-Molina},
  title =       {Disinformation Techniques for Entity Resolution},
  publisher =   {Stanford InfoLab},
  institution = {Stanford University},
  number =      {1014},
  year = 2011
}

@article{Wha11c,
  author =  {Steven Euijong Whang and Hector Garcia-Molina},
  title =   {Developments in Generic Entity Resolution},
  journal = {IEEE Data Engineering Bulletin},
  volume =  34,
  number =  3,
  pages =   {51--59},
  year =    2011
}

@inproceedings{Wha12,
  author =    {Steven Euijong Whang and Hector Garcia-Molina},
  title =     {Joint Entity Resolution},
  booktitle = {IEEE ICDE},
  address =   {Arlington, Virginia},
  year =      2012
}

@inproceedings{Wei04,
  author =    {Weis, M. and Naumann, F.},
  title =     {Detecting duplicate objects in XML documents},
  booktitle = {International Workshop on Information Quality in
               Information Systems},
  address =   {Paris},
  pages =     {10--19},
  year =      2004
}

@inproceedings{Wei05,
  title =     {DogmatiX tracks down duplicates in {XML}},
  author =    {Weis, M. and Naumann, F.},
  booktitle = {ACM SIGMOD},
  address =   {Baltimore},
  pages =     {431--442},
  year =      2005
}

@inproceedings{Wei06,
  author =    {Weis, M. and Naumann, F. and Brosy, F.},
  title =     {A duplicate detection benchmark for {XML} (and
               relational) data},
  booktitle = {Workshop on Information Quality for Information
               Systems (IQIS)},
  address =   {Chicago},
  year =      2006
}

@article{Wei08,
  author =  {Melanie Weis and Felix Naumann and Ulrich Jehle and
             Jens Lufter and Holger Schuster},
  title =   {Industry-scale duplicate detection},
  journal = {Proceedings of the VLDB Endowment},
  volume =  1,
  number =  2,
  pages =   {1253--1264},
  year =    2008
}

@book{Wes07,
  title =     {Introduction to graph theory},
  author =    {West, Douglas},
  publisher = {Prentice Hall},
  edition =   3,
  year =      2007
}

@article{Wil09,
  title =   {Rattle: a data mining {GUI} for {R}},
  author =  {Williams, Graham J.},
  journal = {The {R} Journal},
  volume =  1,
  number =  2,
  pages =   {45--55},
  year =    2009
}

@inproceedings{Win90,
  title =     {String Comparator Metrics and Enhanced Decision Rules
               in the {Fellegi-Sunter} Model of Record Linkage},
  author =    {Winkler, W.E.},
  booktitle = {Proceedings of the Section on Survey Research
               Methods},
  publisher = {American Statistical Association},
  pages =     {354--359},
  year =      1990
}

@techreport{Win91,
  author =      {William E. Winkler and Yves Thibaudeau},
  title =       {An Application of the {F}ellegi-{S}unter Model of
                 Record Linkage to the 1990 {U.S}.\ Decennial Census},
  number =      {RR1991/09},
  institution = {US Bureau of the Census},
  address =     {Washington, DC},
  year =        1991
}

@techreport{Win00,
  title =       {Using the {EM} algorithm for weight computation in
                 the {Fellegi-Sunter} model of record linkage},
  author =      {William E. Winkler},
  number =      {RR2000/05},
  institution = {US Bureau of the Census},
  address =     {Washington, DC},
  year =        2000
}

@techreport{Win01,
  author =      {William E. Winkler},
  title =       {Record linkage software and methods for merging
                 administrative lists},
  number =      {RR2001/03},
  institution = {US Bureau of the Census},
  address =     {Washington, DC},
  year =        2001
}

@techreport{Win02,
  author =      {William E. Winkler},
  title =       {Methods for record linkage and {Bayesian} networks},
  number =      {RR2002/05},
  institution = {US Bureau of the Census},
  address =     {Washington, DC},
  year =        2001
}

@article{Win04,
  author =  {William E. Winkler},
  title =   {Methods for Evaluating and Creating Data Quality},
  journal = {Elsevier Information Systems},
  volume =  29,
  number =  7,
  pages =   {531--550},
  year =    2004
}

@techreport{Win05,
  author =      {William E. Winkler},
  title =       {Approximate String Comparator Search Strategies
                 for Very Large Administrative Lists},
  number =      {RR2005/02},
  institution = {US Bureau of the Census},
  address =     {Washington, DC},
  year =        2005
}

@techreport{Win06,
  author =      {William E. Winkler},
  title =       {Overview of Record Linkage and Current Research
                 Directions},
  number =      {RR2006/02},
  institution = {US Bureau of the Census},
  address =     {Washington, DC},
  year =        2006
}

@techreport{Win07,
  author =      {William E. Winkler},
  title =       {Automatic Estimation of Record Linkage False Match
                 Rates},
  number =      {RR2007/05},
  institution = {US Bureau of the Census},
  address =     {Washington, DC},
  year =        2007
}

@inproceedings{Win10,
  author =    {William E. Winkler and William E. Yancey and Edward H.
               Porter},
  title =     {Fast Record Linkage of Very Large Files in Support of
               Decennial and Administrative Records Projects},
  booktitle = {Proceedings of the Section on Survey Research Methods},
  publisher = {American Statistical Association},
  pages =     {2120--2130},
  year =      2010
}

@Book{Wit99,
  author =    {Ian H. Witten and Alistair Moffat and Timothy C. Bell},
  title =     {Managing Gigabytes},
  publisher = {Morgan Kaufmann},
  edition =   2,
  year =      {1999}
}

@article{Xia08,
  author =  {Chuan Xiao and Wei Wang and Xuemin Lin},
  title =   {Ed-Join: an efficient algorithm for similarity joins
             with edit distance constraints},
  journal = {Proceedings of the VLDB Endowment},
  volume =  1,
  number =  1,
  pages =   {933--944},
  year =    2008
}

@inproceedings{Yak09,
  title =     {Efficient private record linkage},
  author =    {Mohamed Yakout and Mikhail J. Atallah and Ahmed K.
               Elmagarmid},
  booktitle = {IEEE ICDE},
  address =   {Shanghai},
  pages =     {1283--1286},
  year =      2009
}

@article{Yak10,
  title =     {Behavior based record linkage},
  author =    {Yakout, M. and Elmagarmid, A.K. and Elmeleegy, H.
               and Ouzzani, M. and Qi, A.},
  journal =   {Proceedings of the VLDB Endowment},
  publisher = {VLDB Endowment},
  volume =    3,
  number =    {1-2},
  pages =     {439--448},
  year =      2010
}

@techreport{Yan07,
  author =      {William E. Yancey},
  title =       {{BigMatch}: A program for extracting probable matches
                 from a large file for record linkage},
  number =      {RRC2007/01},
  institution = {US Bureau of the Census},
  year =        2007
}

@techreport{Yan04,
  author =      {Yancey, William E.},
  title =       {An adaptive string comparator for record linkage},
  number =      {RR2004/02},
  institution = {US Bureau of the Census},
  year =        2004
}

@techreport{Yan05,
  author =      {Yancey, William E.},
  title =       {Evaluating string comparator performance for record
                 linkage},
  number =      {RR2005/05},
  institution = {US Bureau of the Census},
  year =        2005
}

@inproceedings{Yan07b,
  author =    {Yan, Su and Lee, Dongwon and Kan, Min-Yen and Giles,
               C. Lee},
  title =     {Adaptive sorted neighborhood methods for efficient
               record linkage},
  booktitle = {ACM/IEEE-CS joint conference on Digital Libraries},
  address =   {Vancouver},
  pages =     {185--194},
  year =      2007
}

@book{Yu10,
  author =    {Yu, P.S. and Han, J. and Faloutsos, C.},
  title =     {Link Mining: Models, Algorithms, and Applications},
  publisher = {Springer},
  year =      2010
}

@book{Zak00,
  title =     {Large-scale parallel data mining},
  author =    {Zaki, M.J. and Ho, C.T.},
  number =    {Springer LNCS 1759},
  year =      2000
}

@article{Zha07,
  author =    {Zhao, H.},
  title =     {Semantic matching across heterogeneous data sources},
  journal =   {Communications of the ACM},
  volume =    50,
  number =    1,
  pages =     {45--50},
  issn =      {0001-0782},
  publisher = {ACM},
  year =      2007
}

@article{Zha10,
  author =   {Ying Zhang and Xuemin Lin and Wenjie Zhang and Jianmin
              Wang and Qianlu Lin},
  title =    {Effectively Indexing the Uncertain Space},
  journal =  {IEEE Transactions on Knowledge and Data Engineering},
  volume =   22,
  number =   9,
  pages =    {1247--1261},
  year =     2010
}

@inproceedings{Zhu00,
  author =    {Zhu, Joanne J. and Ungar, Lyle H.},
  title =     {String edit analysis for merging databases},
  booktitle = {KDD workshop on text mining, held at ACM SIGKDD},
  address =   {Boston},
  year =      2000
}

@article{Zin04,
  author =  {Zingmond, D.S. and Ye, Z. and Ettner, S.L. and Liu H.},
  title =   {Linking hospital discharge and death records -- Accuracy
             and sources of bias},
  journal = {Journal of Clinical Epidemiology},
  volume =  57,
  pages =   {21--29},
  year =    2004
}

@inproceedings{Zob96,
  author =    {Zobel, Justin and Dart, Philip},
  title =     {Phonetic string matching: Lessons from information
               retrieval},
  booktitle = {ACM SIGIR},
  address =   {Z\"urich, Switzerland},
  pages =     {166--172},
  year =      1996
}

@article{Zob06,
  author =  {Zobel, Justin and Moffat, A.},
  title =   {Inverted files for text search engines},
  journal = {ACM Computing Surveys},
  volume =  38,
  number =  2,
  pages =   6,
  year=     2006
}