Extracting Parallel Sentences with Bidirectional Recurrent Neural Networks to Improve Machine Translation

Francis Grégoire, Philippe Langlais


Abstract
Parallel sentence extraction is a task addressing the data sparsity problem found in multilingual natural language processing applications. We propose a bidirectional recurrent neural network based approach to extract parallel sentences from collections of multilingual texts. Our experiments with noisy parallel corpora show that we can achieve promising results against a competitive baseline by removing the need of specific feature engineering or additional external resources. To justify the utility of our approach, we extract sentence pairs from Wikipedia articles to train machine translation systems and show significant improvements in translation performance.
Anthology ID:
C18-1122
Volume:
Proceedings of the 27th International Conference on Computational Linguistics
Month:
August
Year:
2018
Address:
Santa Fe, New Mexico, USA
Editors:
Emily M. Bender, Leon Derczynski, Pierre Isabelle
Venue:
COLING
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1442–1453
Language:
URL:
https://aclanthology.org/C18-1122
DOI:
Bibkey:
Cite (ACL):
Francis Grégoire and Philippe Langlais. 2018. Extracting Parallel Sentences with Bidirectional Recurrent Neural Networks to Improve Machine Translation. In Proceedings of the 27th International Conference on Computational Linguistics, pages 1442–1453, Santa Fe, New Mexico, USA. Association for Computational Linguistics.
Cite (Informal):
Extracting Parallel Sentences with Bidirectional Recurrent Neural Networks to Improve Machine Translation (Grégoire & Langlais, COLING 2018)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl24-info/C18-1122.pdf
Code
 FrancisGregoire/parSentExtract
Data
Europarl