Improving Diachronic Word Sense Induction with a Nonparametric Bayesian method - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Improving Diachronic Word Sense Induction with a Nonparametric Bayesian method

Résumé

Diachronic Word Sense Induction (DWSI) is the task of inducing the temporal representations of a word meaning from the context, as a set of senses and their prevalence over time. We introduce two new models for DWSI, based on topic modelling techniques: one is based on Hierarchical Dirichlet Processes (HDP), a nonparametric model; the other is based on the Dynamic Embedded Topic Model (DETM), a recent dynamic neural model. We evaluate these models against two state of the art DWSI models, using a time-stamped labelled dataset from the biomedical domain. We demonstrate that the two proposed models perform better than the state of the art. In particular, the HDP-based model drastically outperforms all the other models, including the dynamic neural models. 1

Domaines

Informatique
Fichier principal
Vignette du fichier
2023.findings-acl.567.pdf (1.18 Mo) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte
Licence : CC BY - Paternité

Dates et versions

hal-04439169 , version 1 (07-02-2024)

Licence

Paternité

Identifiants

Citer

Ashjan Alsulaimani, Erwan Moreau. Improving Diachronic Word Sense Induction with a Nonparametric Bayesian method. Findings of the Association for Computational Linguistics: ACL 2023, Jul 2023, Toronto, Canada. pp.8908-8925, ⟨10.18653/v1/2023.findings-acl.567⟩. ⟨hal-04439169⟩
7 Consultations
7 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More