\'Evolution phonologique des langues et r\'eseaux de neurones : travaux pr\'eliminaires (Sound change and neural networks: preliminary experiments )

1 code implementation • JEPTALNRECITAL 2020 • Cl{\'e}mentine Fourrier

Dans ce papier, nous {\'e}tudions donc la performance des m{\'e}thodes neuronales utilis{\'e}es en traduction (les r{\'e}seaux encodeur-d{\'e}codeur) pour la t{\^a}che de pr{\'e}diction de cognats.

Comparing Statistical and Neural Models for Learning Sound Correspondences

1 code implementation • LREC 2020 • Cl{\'e}mentine Fourrier, Beno{\^\i}t Sagot

Cognate prediction and proto-form reconstruction are key tasks in computational historical linguistics that rely on the study of sound change regularity.

Cognate Prediction Machine Translation +1

Methodological Aspects of Developing and Managing an Etymological Lexical Resource: Introducing EtymDB-2.0

1 code implementation • LREC 2020 • Cl{\'e}mentine Fourrier, Beno{\^\i}t Sagot

Diachronic lexical information is not only important in the field of historical linguistics, but is also increasingly used in NLP, most recently for machine translation of low resource languages.

Cognate Prediction Machine Translation +1