Word2Vec vs DBnary: Augmenting METEOR using Vector Representations or Lexical Resources?

Abstract : This paper presents an approach combining lexico-semantic resources and distributed representations of words applied to the evaluation in machine translation (MT). This study is made through the enrichment of a well-known MT evaluation metric: METEOR. This metric enables an approximate match (synonymy or morphological similarity) between an automatic and a reference translation. Our experiments are made in the framework of the Metrics task of WMT 2014. We show that distributed representations are a good alternative to lexico-semantic resources for MT evaluation and they can even bring interesting additional information. The augmented versions of METEOR, using vector representations, are made available on our Github page.
Type de document :
Communication dans un congrès
COLING 2016, Dec 2016, Osaka, Japan. 26th International Conference on Computational Linguistics (COLING 2016), 2016
Liste complète des métadonnées

Littérature citée [40 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-01376948
Contributeur : Laurent Besacier <>
Soumis le : vendredi 7 octobre 2016 - 10:34:20
Dernière modification le : jeudi 11 octobre 2018 - 08:48:03
Document(s) archivé(s) le : dimanche 8 janvier 2017 - 12:21:08

Fichier

metrics_enhanced_COLING2016.pd...
Fichiers produits par l'(les) auteur(s)

Licence


Distributed under a Creative Commons CC0 - Transfert dans le Domaine Public 4.0 International License

Identifiants

  • HAL Id : hal-01376948, version 1
  • ARXIV : 1610.01291

Citation

Christophe Servan, Alexandre Bérard, Zied Elloumi, Hervé Blanchon, Laurent Besacier. Word2Vec vs DBnary: Augmenting METEOR using Vector Representations or Lexical Resources?. COLING 2016, Dec 2016, Osaka, Japan. 26th International Conference on Computational Linguistics (COLING 2016), 2016. 〈hal-01376948〉

Partager

Métriques

Consultations de la notice

794

Téléchargements de fichiers

261