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.- Anthology ID:
- 2022.findings-acl.299
- Volume:
- Findings of the Association for Computational Linguistics: ACL 2022
- Month:
- May
- Year:
- 2022
- Address:
- Dublin, Ireland
- Editors:
- Smaranda Muresan, Preslav Nakov, Aline Villavicencio
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 3786–3801
- Language:
- URL:
- https://aclanthology.org/2022.findings-acl.299
- DOI:
- 10.18653/v1/2022.findings-acl.299
- Cite (ACL):
- Clémentine Fourrier and Benoît Sagot. 2022. Probing Multilingual Cognate Prediction Models. In Findings of the Association for Computational Linguistics: ACL 2022, pages 3786–3801, Dublin, Ireland. Association for Computational Linguistics.
- Cite (Informal):
- Probing Multilingual Cognate Prediction Models (Fourrier & Sagot, Findings 2022)
- PDF:
- https://preview.aclanthology.org/naacl24-info/2022.findings-acl.299.pdf