This repository contains some basic methods for Aspect Extraction, as denoted in Step 1
of this research statement.
.
├── README.md
├── config # config files
├── data # compressed and decompressed txt data
├── label # manually attached labels to use as test set
├── output # generated output with file extension `*.keywords`
└── src # code
id | paper | code | supervised | result |
---|---|---|---|---|
mate | Angelidis and Lapata, Summarizing Opinions: Aspect Extraction Meets Sentiment Prediction and They Are Both Weakly Supervised, | https://github.com/stangelid/oposum | semi- | on keyboard dataset from electronic data mate.jsonl |
acos | Cai et al., Aspect-Category-Opinion-Sentiment Quadruple Extraction with Implicit Aspects and Opinions, ACL 2021 | https://github.com/NUSTM/ACOS | yes | |
cat | Embarrassingly Simple Unsupervised Aspect Extraction, ACL 2020 | https://github.com/clips/cat | no | |
AspMem | Chao Zhao and Snigdha Chaturvedi, Weakly-Supervised Opinion Summarization by Leveraging External Information, AAAI 2020 | https://github.com/zhaochaocs/AspMem | no | on keyboard dataset from electronic data aspmem.json |
pip install -r requirements.txt
cd src
python main.py