Word2Vec vs DBnary ou comment (ré)concilier représentations distribuées et réseaux lexico-sémantiques ? Le cas de l’évaluation en traduction automatique

Abstract : This paper presents an approach combining lexical-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. METEOR 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 less efficient than lexical-semantic resources for MT evaluation but they can nonetheless bring interesting additional information.
Document type :
Conference papers
Liste complète des métadonnées

Cited literature [34 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01350101
Contributor : Laurent Besacier <>
Submitted on : Sunday, August 21, 2016 - 9:12:56 AM
Last modification on : Thursday, April 4, 2019 - 10:18:05 AM
Document(s) archivé(s) le : Tuesday, November 22, 2016 - 10:26:04 AM

File

T10.pdf
Publication funded by an institution

Identifiers

  • HAL Id : hal-01350101, version 1

Collections

Citation

Christophe Servan, Zied Elloumi, Hervé Blanchon, Laurent Besacier. Word2Vec vs DBnary ou comment (ré)concilier représentations distribuées et réseaux lexico-sémantiques ? Le cas de l’évaluation en traduction automatique. TALN 2016, Jul 2016, Paris, France. Actes de la conférence conjointe JEP-TALN-RECITAL. 〈hal-01350101〉

Share

Metrics

Record views

301

Files downloads

511