Learning grounded word meaning representations on similarity graphs - IRIT - Centre National de la Recherche Scientifique Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Learning grounded word meaning representations on similarity graphs

Résumé

This paper introduces a novel approach to learn visually grounded meaning representations of words as low-dimensional node embeddings on an underlying graph hierarchy. The lower level of the hierarchy models modality-specific word representations through dedicated but communicating graphs, while the higher level puts these representations together on a single graph to learn a representation jointly from both modalities. The topology of each graph models similarity relations among words, and is estimated jointly with the graph embedding. The assumption underlying this model is that words sharing similar meaning correspond to communities in an underlying similarity graph in a lowdimensional space. We named this model Hierarchical Multi-Modal Similarity Graph Embedding (HM-SGE). Experimental results validate the ability of HM-SGE to simulate human similarity judgements and concept categorization, outperforming the state of the art. 1 * Work done during an internship at the IRI (CSIC-UPC).
Fichier principal
Vignette du fichier
emnlp2021.pdf (2.05 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03381921 , version 1 (18-10-2021)

Identifiants

Citer

Mariella Dimiccoli, Herwig Wendt, Pau Batlle. Learning grounded word meaning representations on similarity graphs. Conference on Empirical Methods in Natural Language Processing (EMNLP 2021), Nov 2021, Punta Cana, Dominican Republic. ⟨hal-03381921⟩
141 Consultations
46 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More