Skip to Main content Skip to Navigation
Conference papers

Évolution phonétique des langues et réseaux de neurones : travaux préliminaires

Abstract : Cognate prediction is a key task in historical linguistics that presents a number of similarities withmachine translation. However, although neural methods are now widespread in machine translation,they are still largely unused in historical linguistics. In this paper, we study the performance ofneural methods (more specifically encoder-decoder networks) for the task of cognate prediction. Wefocus in particular on the types of data that can be used for this task, and compare the performanceof statistical and neural methods. We show that sound correspondances can only be learned usingcognate datasets, and that statistical and neural methods seem to have complementary strengths andweaknesses regarding what they learn about the data.
Document type :
Conference papers
Complete list of metadata

Cited literature [21 references]  Display  Hide  Download
Contributor : Sylvain Pogodalla Connect in order to contact the contributor
Submitted on : Tuesday, June 23, 2020 - 11:42:28 AM
Last modification on : Wednesday, June 8, 2022 - 12:50:06 PM


Publisher files allowed on an open archive


  • HAL Id : hal-02786192, version 3


Clémentine Fourrier. Évolution phonétique des langues et réseaux de neurones : travaux préliminaires. JEP-TALN-RECITAL 2020 - 33ème Journées d’Études sur la Parole, 27ème Conférence sur le Traitement Automatique des Langues Naturelles, 22ème Rencontre des Étudiants Chercheurs en Informatique pour le Traitement Automatique des Langues, Jun 2020, Nancy / Virtuel, France. pp.110-122. ⟨hal-02786192v3⟩



Record views


Files downloads