Ctrl K

What does a Text Classifier Learn about Morality? An Explainable Method for Cross-Domain Comparison of Moral Rhetoric - code

What does a Text Classifier Learn about Morality? An Explainable Method for Cross-Domain Comparison of Moral Rhetoric - code

12
mentions
7
contributors

Description

Code for the paper "What does a Text Classifier Learn about Morality? An Explainable Method for Cross-Domain Comparison of Moral Rhetoric", published at ACL '23. This code implements Tomea, an Explainable AI method for investigating the difference in how language models represent morality across domains. Given a pair of datasets and models trained on the datasets, Tomea generates 10 m-distances and one d-distance to measure the difference between the datasets, based on the SHAP method. We make pairwise comparisons of seven models trained on the MFTC datasets (available at this DOI: 10.4121/646b20e3-e24f-452d-938a-bcb6ce30913c).

Logo of What does a Text Classifier Learn about Morality? An Explainable Method for Cross-Domain Comparison of Moral Rhetoric - code
Keywords
Ethics
explainable artificial intelligence
Morality
Natural Language Processing
NLP
XAI
Programming languages
License
  • MIT
</>Source code
Packages

Reference papers

Mentions

Contributors

C(J

Member of community

4TU