Probing Multilingual Cognate Prediction Models
Résumé
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.
Fichier principal
ACL2022_Fourrier and Sagot_Probing Multilingual Cognate Prediction Models.pdf (891.93 Ko)
Télécharger le fichier
Origine | Fichiers produits par l'(les) auteur(s) |
---|