Skip to content

README.md

Latest commit

 

History

History
56 lines (39 loc) · 2.72 KB

README.md

File metadata and controls

56 lines (39 loc) · 2.72 KB
Raw

Interlocking-free Selective Rationalization Through Genetic-based Learning

Official repository of "Interlocking-free Selective Rationalization Through Genetic-based Learning".

Structure

We split GenSPP and selective rationalization baselines in two standalone projects: genetic, and baselines.

Genetic

Please, see the README.md file in genetic folder.

Baselines

Please, see the README.md file in baseline folder.

Issues

Don't hesitate to file an issue if you find some bugs!

Contact

Cite

@inproceedings{ruggeri-signorelli-2025-interlocking,
    title = "Interlocking-free Selective Rationalization Through Genetic-based Learning",
    author = "Ruggeri, Federico  and
      Signorelli, Gaetano",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.acl-long.59/",
    doi = "10.18653/v1/2025.acl-long.59",
    pages = "1175--1191",
    ISBN = "979-8-89176-251-0",
    abstract = "A popular end-to-end architecture for selective rationalization is the select-then-predict pipeline, comprising a generator to extract highlights fed to a predictor. Such a cooperative system suffers from suboptimal equilibrium minima due to the dominance of one of the two modules, a phenomenon known as interlocking. While several contributions aimed at addressing interlocking, they only mitigate its effect, often by introducing feature-based heuristics, sampling, and ad-hoc regularizations. We present GenSPP, the first interlocking-free architecture for selective rationalization that does not require any learning overhead, as the above-mentioned. GenSPP avoids interlocking by performing disjoint training of the generator and predictor via genetic global search. Experiments on a synthetic and a real-world benchmark show that our model outperforms several state-of-the-art competitors."
}

Credits

Eleonora Misino, Paolo Torroni

Acknowledgments

This publication is supported by the project European Commission’s NextGeneration EU programme, PNRR – M4C2 – Investimento 1.3, Partenariato Esteso, PE00000013 - “FAIR - Future Artificial Intelligence Research” – Spoke 8 “Pervasive AI” and by the European Union’s Justice Programme under Grant Agreement No. 101087342 for the project “Principles Of Law In National and European VAT”.