Detecting Cross-Lingual Semantic Divergence for Neural Machine Translation

Marine Carpuat, Yogarshi Vyas, Xing Niu


Abstract
Parallel corpora are often not as parallel as one might assume: non-literal translations and noisy translations abound, even in curated corpora routinely used for training and evaluation. We use a cross-lingual textual entailment system to distinguish sentence pairs that are parallel in meaning from those that are not, and show that filtering out divergent examples from training improves translation quality.
Anthology ID:
W17-3209
Volume:
Proceedings of the First Workshop on Neural Machine Translation
Month:
August
Year:
2017
Address:
Vancouver
Venues:
NGT | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
69–79
Language:
URL:
https://www.aclweb.org/anthology/W17-3209
DOI:
10.18653/v1/W17-3209
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/W17-3209.pdf