Probing Multilingual Cognate Prediction Models

Clémentine Fourrier; Benoît Sagot

ACL 2022findings7 citations

Probing Multilingual Cognate Prediction Models

Abstract

Character-based neural machine translation models have become the reference models for cognate prediction, a historical linguistics task. So far, all linguistic interpretations about latent information captured by such models have been based on external analysis (accuracy, raw results, errors). In this paper, we investigate what probing can tell us about both models and previous interpretations, and learn that though our models store linguistic and diachronic information, they do not achieve it in previously assumed ways.

BibTeX

@inproceedings{fourrier-sagot-2022-probing,
    title = "Probing Multilingual Cognate Prediction Models",
    author = "Fourrier, Cl{\'e}mentine  and
      Sagot, Beno{\^i}t",
    editor = "Muresan, Smaranda  and
      Nakov, Preslav  and
      Villavicencio, Aline",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2022",
    month = may,
    year = "2022",
    address = "Dublin, Ireland",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2022.findings-acl.299/",
    doi = "10.18653/v1/2022.findings-acl.299",
    pages = "3786--3801"
}