Probing Multilingual Cognate Prediction Models - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2022

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.
Fichier principal
Vignette du fichier
ACL2022_Fourrier and Sagot_Probing Multilingual Cognate Prediction Models.pdf (891.93 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03614691 , version 1 (21-03-2022)

Identifiers

  • HAL Id : hal-03614691 , version 1

Cite

Clémentine Fourrier, Benoît Sagot. Probing Multilingual Cognate Prediction Models. ACL 2022 - Findings of the Association for Computational Linguistics, May 2022, Dublin, Ireland. ⟨hal-03614691⟩
78 View
217 Download

Share

Gmail Facebook X LinkedIn More