Monitoring geometrical properties of word embeddings for detecting the emergence of new topics - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Monitoring geometrical properties of word embeddings for detecting the emergence of new topics

Clément Christophe
  • Fonction : Auteur
  • PersonId : 1099268
Manel Boumghar
  • Fonction : Auteur
  • PersonId : 1072396
Philippe Suignard

Résumé

Slow emerging topic detection is a task between event detection, where we aggregate behaviors of different words on short period of time, and language evolution, where we monitor their long term evolution. In this work, we tackle the problem of early detection of slowly emerging new topics. To this end, we gather evidence of weak signals at the word level. We propose to monitor the behavior of words representation in an embedding space and use one of its geometrical properties to characterize the emergence of topics. As evaluation is typically hard for this kind of task, we present a framework for quantitative evaluation. We show positive results that outperform state-ofthe-art methods on two public datasets of press and scientific articles.
Fichier principal
Vignette du fichier
EMNLP_2021_CameraReady__Monitoring_geometrical_properties_of_word_embeddings_for_the_detection_of_new_topic_emergence.pdf (1.38 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03699173 , version 1 (20-06-2022)

Identifiants

Citer

Clément Christophe, Julien Velcin, Jairo Cugliari, Manel Boumghar, Philippe Suignard. Monitoring geometrical properties of word embeddings for detecting the emergence of new topics. 2021 Conference on Empirical Methods in Natural Language Processing, Nov 2021, Punta Cana, Dominican Republic. ⟨10.18653/v1/2021.emnlp-main.76⟩. ⟨hal-03699173⟩
17 Consultations
11 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More