METEOR For Multiple Target Languages Using DBnary

Abstract : This paper proposes an extension of METEOR, a well-known MT evaluation metric, for multiple target languages using an in-house lexical resource called DBnary (an extraction from Wiktionary provided to the community as a Multilingual Lexical Linked Open Data). Today, the use of the synonymy module of METEOR is only exploited when English is the target language (use of WordNet). A synonymy module using DBnary would allow its use for the 21 languages (covered up to now) as target languages. The code of this new instance of METEOR, adapted to several target languages, is provided to the community via a github repository. We also show that our DBnary augmented METEOR increases the correlation with human judgements on the WMT 2013 and 2014 metrics dataset for English-to-(French, Russian, German, Spanish) language pairs.
Type de document :
Communication dans un congrès
MT Summit 2015, Nov 2015, Miami, United States. Proceedings of the Summit XV, vol 1
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01350109
Contributeur : Laurent Besacier <>
Soumis le : dimanche 21 août 2016 - 09:08:51
Dernière modification le : jeudi 21 février 2019 - 16:30:06
Document(s) archivé(s) le : mardi 22 novembre 2016 - 10:13:08

Fichier

Elloumi_and_al-METEOR_for_Mult...
Fichiers éditeurs autorisés sur une archive ouverte

Identifiants

  • HAL Id : hal-01350109, version 1

Collections

Citation

Zied Elloumi, Hervé Blanchon, Gilles Serasset, Laurent Besacier. METEOR For Multiple Target Languages Using DBnary. MT Summit 2015, Nov 2015, Miami, United States. Proceedings of the Summit XV, vol 1. 〈hal-01350109〉

Partager

Métriques

Consultations de la notice

405

Téléchargements de fichiers

128