Filtering communities in word co-occurrence networks to foster the emergence of meaning - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Filtering communities in word co-occurrence networks to foster the emergence of meaning

Résumé

With SINr, we introduced a way to design graph and word embeddings based on community detection. Contrary to deep learning approaches, this approach does not require much compute and was proven to be at the state-of-the-art for interpretability in the context of word embeddings. In this paper, we investigate how filtering communities detected on word co-occurrence networks can improve performances of the approach. Community detection algorithms tend to uncover communities whose size follows a power-law distribution. Naturally, the number of activations per dimensions in SINr follows a power-law: a few dimensions are activated by many words, and many dimensions are activated by a few words. By filtering this distribution, removing part of its head and tail, we show improvement on intrinsic evaluation of the embedding while dividing their dimensionality by five. In addition, we show that these results are stable through several runs, thus defining a subset of distinctive features to describe a given corpus.
Fichier principal
Vignette du fichier
_DIGING__Complex_Networks_2023__Copy_.pdf (946 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Licence : CC BY - Paternité

Dates et versions

hal-04398742 , version 1 (16-01-2024)

Licence

Paternité

Identifiants

Citer

Anna Béranger, Nicolas Dugué, Simon Guillot, Thibault Prouteau. Filtering communities in word co-occurrence networks to foster the emergence of meaning. Conference on Complex Networks and their Applications, Nov 2023, Menton, France. pp.377-388, ⟨10.1007/978-3-031-53468-3_32⟩. ⟨hal-04398742⟩
32 Consultations
27 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More