Fusing Document, Collection and Label Graph-based Representations with Word Embeddings for Text Classification

Abstract : Contrary to the traditional Bag-of-Words approach, we consider the Graph-of-Words (GoW) model in which each document is represented by a graph that encodes relationships between the different terms. Based on this formulation, the importance of a term is determined by weighting the corresponding node in the document, collection and label graphs, using node centrality criteria. We also introduce novel graph-based weighting schemes by enriching graphs with word-embedding similarities, in order to reward or penalize semantic relationships. Our methods produce more discriminative feature weights for text categorization, out-performing existing frequency-based criteria.
Type de document :
Communication dans un congrès
NAACL-HLT Workshop on Graph-Based Natural Language Processing (TextGraphs), Jun 2018, New Orleans, Louisiana, United States. 〈10.18653/v1/w18-1707 〉
Liste complète des métadonnées

Littérature citée [40 références]  Voir  Masquer  Télécharger

https://hal-centralesupelec.archives-ouvertes.fr/hal-01848880
Contributeur : Fragkiskos Malliaros <>
Soumis le : mercredi 25 juillet 2018 - 12:02:11
Dernière modification le : jeudi 7 février 2019 - 14:38:06
Document(s) archivé(s) le : vendredi 26 octobre 2018 - 13:32:55

Fichier

fusing-document-collection.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Citation

Konstantinos Skianis, Fragkiskos Malliaros, Michalis Vazirgiannis. Fusing Document, Collection and Label Graph-based Representations with Word Embeddings for Text Classification. NAACL-HLT Workshop on Graph-Based Natural Language Processing (TextGraphs), Jun 2018, New Orleans, Louisiana, United States. 〈10.18653/v1/w18-1707 〉. 〈hal-01848880〉

Partager

Métriques

Consultations de la notice

252

Téléchargements de fichiers

40