Extending a probabilistic phrase alignment approach for SMT

Mridul Gupta, Sanjika Hewavitharana, Stephan Vogel


Abstract
Phrase alignment is a crucial step in phrase-based statistical machine translation. We explore a way of improving phrase alignment by adding syntactic information in the form of chunks as soft constraints guided by an in-depth and detailed analysis on a hand-aligned data set. We extend a probabilistic phrase alignment model that extracts phrase pairs by optimizing phrase pair boundaries over the sentence pair [1]. The boundaries of the target phrase are chosen such that the overall sentence alignment probability is optimal. Viterbi alignment information is also added in the extended model with a view of improving phrase alignment. We extract phrase pairs using a relatively larger number of features which are discriminatively trained using a large-margin online learning algorithm, i.e., Margin Infused Relaxed Algorithm (MIRA) and integrate it in our approach. Initial experiments show improvements in both phrase alignment and translation quality for Arabic-English on a moderate-size translation task.
Anthology ID:
2011.iwslt-evaluation.23
Volume:
Proceedings of the 8th International Workshop on Spoken Language Translation: Evaluation Campaign
Month:
December 8-9
Year:
2011
Address:
San Francisco, California
Editors:
Marcello Federico, Mei-Yuh Hwang, Margit Rödder, Sebastian Stüker
Venue:
IWSLT
SIG:
SIGSLT
Publisher:
Note:
Pages:
175–182
Language:
URL:
https://aclanthology.org/2011.iwslt-evaluation.23
DOI:
Bibkey:
Cite (ACL):
Mridul Gupta, Sanjika Hewavitharana, and Stephan Vogel. 2011. Extending a probabilistic phrase alignment approach for SMT. In Proceedings of the 8th International Workshop on Spoken Language Translation: Evaluation Campaign, pages 175–182, San Francisco, California.
Cite (Informal):
Extending a probabilistic phrase alignment approach for SMT (Gupta et al., IWSLT 2011)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-5/2011.iwslt-evaluation.23.pdf