Word2Vec vs DBnary ou comment (ré)concilier représentations distribuées et réseaux lexico-sémantiques ? Le cas de l’évaluation en traduction automatique
Résumé
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.
Domaines
Informatique et langage [cs.CL]
Origine : Publication financée par une institution
Loading...