Bayesian iterative-cascade framework for hierarchical phrase-based translation

Baskaran Sankaran, Anoop Sarkar


Abstract
The typical training of a hierarchical phrase-based machine translation involves a pipeline of multiple steps where mistakes in early steps of the pipeline are propagated without any scope for rectifying them. Additionally the alignments are trained independent of and without being informed of the end goal and hence are not optimized for translation. We introduce a novel Bayesian iterative-cascade framework for training Hiero-style model that learns the alignments together with the synchronous translation grammar in an iterative setting. Our framework addresses the above mentioned issues and provides an elegant and principled alternative to the existing training pipeline. Based on the validation experiments involving two language pairs, our proposed iterative-cascade framework shows consistent gains over the traditional training pipeline for hierarchical translation.
Anthology ID:
2014.amta-researchers.2
Volume:
Proceedings of the 11th Conference of the Association for Machine Translation in the Americas: MT Researchers Track
Month:
October 22-26
Year:
2014
Address:
Vancouver, Canada
Venue:
AMTA
SIG:
Publisher:
Association for Machine Translation in the Americas
Note:
Pages:
15–27
Language:
URL:
https://aclanthology.org/2014.amta-researchers.2
DOI:
Bibkey:
Cite (ACL):
Baskaran Sankaran and Anoop Sarkar. 2014. Bayesian iterative-cascade framework for hierarchical phrase-based translation. In Proceedings of the 11th Conference of the Association for Machine Translation in the Americas: MT Researchers Track, pages 15–27, Vancouver, Canada. Association for Machine Translation in the Americas.
Cite (Informal):
Bayesian iterative-cascade framework for hierarchical phrase-based translation (Sankaran & Sarkar, AMTA 2014)
Copy Citation:
PDF:
https://aclanthology.org/2014.amta-researchers.2.pdf