Skip to content

This code is developed for training and evaluating a model that translates natural language (NL) sentences into First-Order Logic (FOL) expressions using a T5-based model.

Notifications You must be signed in to change notification settings

ieddeveci/NL_to_FOL_T5FineTuning

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

20 Commits
 
 
 
 

Repository files navigation

NL_to_FOL_T5FineTuning

This code is a slightly modified version of the one used for training and evaluating a T5 language model that translates natural language (NL) sentences into First-Order Logic (FOL) expressions in my master's thesis titled "Transformer Models for Translating Natural Language Sentences into Formal Logical Expressions. A more detailed explanation of the code, the task, and the evaluation metrics can also be found in the full thesis.

For the equivalence metric to function properly, Prover9 must be downloaded from the following website: Prover9.

The dataset used for this thesis will be released following the publication of a paper derived from the thesis.

image

About

This code is developed for training and evaluating a model that translates natural language (NL) sentences into First-Order Logic (FOL) expressions using a T5-based model.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published