Using bilingual word-embeddings for multilingual collocation extraction

Marcos Garcia, Marcos García-Salido, Margarita Alonso-Ramos


Abstract
This paper presents a new strategy for multilingual collocation extraction which takes advantage of parallel corpora to learn bilingual word-embeddings. Monolingual collocation candidates are retrieved using Universal Dependencies, while the distributional models are then applied to search for equivalents of the elements of each collocation in the target languages. The proposed method extracts not only collocation equivalents with direct translation between languages, but also other cases where the collocations in the two languages are not literal translations of each other. Several experiments -evaluating collocations with three syntactic patterns- in English, Spanish, and Portuguese show that our approach can effectively extract large pairs of bilingual equivalents with an average precision of about 90%. Moreover, preliminary results on comparable corpora suggest that the distributional models can be applied for identifying new bilingual collocations in different domains.
Anthology ID:
W17-1703
Volume:
Proceedings of the 13th Workshop on Multiword Expressions (MWE 2017)
Month:
April
Year:
2017
Address:
Valencia, Spain
Venue:
MWE
SIG:
SIGLEX
Publisher:
Association for Computational Linguistics
Note:
Pages:
21–30
Language:
URL:
https://aclanthology.org/W17-1703
DOI:
10.18653/v1/W17-1703
Bibkey:
Cite (ACL):
Marcos Garcia, Marcos García-Salido, and Margarita Alonso-Ramos. 2017. Using bilingual word-embeddings for multilingual collocation extraction. In Proceedings of the 13th Workshop on Multiword Expressions (MWE 2017), pages 21–30, Valencia, Spain. Association for Computational Linguistics.
Cite (Informal):
Using bilingual word-embeddings for multilingual collocation extraction (Garcia et al., MWE 2017)
Copy Citation:
PDF:
https://aclanthology.org/W17-1703.pdf
Data
OpenSubtitlesUniversal Dependencies