Abstract
Alignment from comparable corpora usually involves two languages, one source and one target language. Previous works on bilingual lexicon extraction from parallel corpora demonstrated that more than two languages can be useful to improve the alignments. Our works have investigated to which extent a third language could be interesting to bypass the original alignment. We have defined two original alignment approaches involving pivot languages and we have evaluated over four languages and two pivot languages in particular. The experiments have shown that in some cases the quality of the extracted lexicon has been enhanced.
Cite
CITATION STYLE
Linard, A., Daille, B., & Morin, E. (2015). Attempting to Bypass Alignment from Comparable Corpora via Pivot Language. In 8th Workshop on Building and Using Comparable Corpora, BUCC 2015 - co-located with 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing, ACL-IJCNLP 2015 - Proceedings (pp. 32–37). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/w15-3405
Register to see more suggestions
Mendeley helps you to discover research relevant for your work.
