Identifying Infrequent Translations by Aligning Non Parallel Sentences

Julien Bourdaillet, Philippe Langlais


Abstract
Aligning a sequence of words to one of its infrequent translations is a difficult task. We propose a simple and original solution to this problem that yields to significant gains over a state-of-the-art transpotting task. Our approach consists in aligning non parallel sentences from the training data in order to reinforce online the alignment models. We show that using only a few pairs of non parallel sentences allows to improve significantly the alignment of infrequent translations.
Anthology ID:
2012.amta-papers.2
Volume:
Proceedings of the 10th Conference of the Association for Machine Translation in the Americas: Research Papers
Month:
October 28-November 1
Year:
2012
Address:
San Diego, California, USA
Venue:
AMTA
SIG:
Publisher:
Association for Machine Translation in the Americas
Note:
Pages:
Language:
URL:
https://aclanthology.org/2012.amta-papers.2
DOI:
Bibkey:
Cite (ACL):
Julien Bourdaillet and Philippe Langlais. 2012. Identifying Infrequent Translations by Aligning Non Parallel Sentences. In Proceedings of the 10th Conference of the Association for Machine Translation in the Americas: Research Papers, San Diego, California, USA. Association for Machine Translation in the Americas.
Cite (Informal):
Identifying Infrequent Translations by Aligning Non Parallel Sentences (Bourdaillet & Langlais, AMTA 2012)
Copy Citation:
PDF:
https://aclanthology.org/2012.amta-papers.2.pdf