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

Christophe Servan, Alexandre Bérard, Zied Elloumi, Hervé Blanchon, Laurent Besacier


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. 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 a good alternative to lexico-semanticresources 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.
Anthology ID:
C16-1110
Volume:
Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers
Month:
December
Year:
2016
Address:
Osaka, Japan
Editors:
Yuji Matsumoto, Rashmi Prasad
Venue:
COLING
SIG:
Publisher:
The COLING 2016 Organizing Committee
Note:
Pages:
1159–1168
Language:
URL:
https://aclanthology.org/C16-1110
DOI:
Bibkey:
Cite (ACL):
Christophe Servan, Alexandre Bérard, Zied Elloumi, Hervé Blanchon, and Laurent Besacier. 2016. Word2Vec vs DBnary: Augmenting METEOR using Vector Representations or Lexical Resources?. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pages 1159–1168, Osaka, Japan. The COLING 2016 Organizing Committee.
Cite (Informal):
Word2Vec vs DBnary: Augmenting METEOR using Vector Representations or Lexical Resources? (Servan et al., COLING 2016)
Copy Citation:
PDF:
https://aclanthology.org/C16-1110.pdf
Code
 cservan/METEOR-E
Data
WMT 2014