Paper: Using WordNet and Semantic Similarity for Bilingual Terminology Mining from Comparable Corpora

ACL ID W13-2503
Title Using WordNet and Semantic Similarity for Bilingual Terminology Mining from Comparable Corpora
Venue Building and Using Comparable Corpora
Session
Year 2013
Authors

This paper presents an extension of the standard approach used for bilingual lex- icon extraction from comparable corpora. We study of the ambiguity problem re- vealed by the seed bilingual dictionary used to translate context vectors. For this purpose, we augment the standard ap- proach by a Word Sense Disambiguation process relying on a WordNet-based se- mantic similarity measure. The aim of this process is to identify the translations that are more likely to give the best rep- resentation of words in the target lan- guage. On two specialized French-English comparable corpora, empirical experimen- tal results show that the proposed method consistently outperforms the standard ap- proach.