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.
Document type :
Conference papers
Liste complète des métadonnées

Cited literature [40 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01376948
Contributor : Laurent Besacier <>
Submitted on : Friday, October 7, 2016 - 10:34:20 AM
Last modification on : Thursday, April 4, 2019 - 10:18:05 AM
Document(s) archivé(s) le : Sunday, January 8, 2017 - 12:21:08 PM

File

metrics_enhanced_COLING2016.pd...
Files produced by the author(s)

Licence


Distributed under a Creative Commons CC0 - Public Domain Dedication 4.0 International License

Identifiers

  • 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, ANLP & ICCL, Dec 2016, Osaka, Japan. ⟨hal-01376948⟩

Share

Metrics

Record views

948

Files downloads

335