Multi-label, Multi-class Classification Using Polylingual Embeddings

Georgios Balikas 1, 2 Massih-Reza Amini 1
1 AMA - Analyse de données, Modélisation et Apprentissage automatique [Grenoble]
LIG - Laboratoire d'Informatique de Grenoble
2 Coffreo
Abstract : We propose a Polylingual text Embedding (PE) strategy, that learns a language independent representation of texts using Neu-ral Networks. We study the effects of bilingual representation learning for text classification and we empirically show that the learned representations achieve better classification performance compared to traditional bag-of-words and other monolingual distributed representations. The performance gains are more significant in the interesting case where only few labeled examples are available for training the classifiers.
Type de document :
Communication dans un congrès
38th European Conference on Information Retrieval ECIR 2016, Mar 2016, Padoue, Italy. Springer, Advances in Information Retrieval 38th European Conference on IR Research, ECIR 2016, Padua, Italy, March 20-23, 2016. Proceedings, 9626, 2016, <10.1007/978-3-319-30671-1_59>
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01299850
Contributeur : Georgios Balikas <>
Soumis le : mercredi 20 avril 2016 - 18:37:53
Dernière modification le : samedi 23 avril 2016 - 01:02:40
Document(s) archivé(s) le : lundi 14 novembre 2016 - 22:25:02

Fichier

paper.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

LIG | UGA

Citation

Georgios Balikas, Massih-Reza Amini. Multi-label, Multi-class Classification Using Polylingual Embeddings. 38th European Conference on Information Retrieval ECIR 2016, Mar 2016, Padoue, Italy. Springer, Advances in Information Retrieval 38th European Conference on IR Research, ECIR 2016, Padua, Italy, March 20-23, 2016. Proceedings, 9626, 2016, <10.1007/978-3-319-30671-1_59>. <hal-01299850>

Exporter

BibTeX TEI DC DCterms EndNote

Partager

Métriques

Consultations de
la notice

133

Téléchargements du document

161

Contact

support.ccsd.cnrs.fr
hal.support@ccsd.cnrs.fr
Logo CCSD