A probabilistic feature-based fill-up for SMT

Jian Zhang, Liangyou Li, Andy Way, Qun Liu


Abstract
In this paper, we describe an effective translation model combination approach based on the estimation of a probabilistic Support Vector Machine (SVM). We collect domain knowledge from both in-domain and general-domain corpora inspired by a commonly used data selection algorithm, which we then use as features for the SVM training. Drawing on previous work on binary-featured phrase table fill-up (Nakov, 2008; Bisazza et al., 2011), we substitute the binary feature in the original work with our probabilistic domain-likeness feature. Later, we design two experiments to evaluate the proposed probabilistic feature-based approach on the French-to-English language pair using data provided at WMT07, WMT13 and IWLST11 translation tasks. Our experiments demonstrate that translation performance can gain significant improvements of up to +0.36 and +0.82 BLEU scores by using our probabilistic feature-based translation model fill-up approach compared with the binary featured fill-up approach in both experiments.
Anthology ID:
2014.amta-researchers.8
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
Editors:
Yaser Al-Onaizan, Michel Simard
Venue:
AMTA
SIG:
Publisher:
Association for Machine Translation in the Americas
Note:
Pages:
96–109
Language:
URL:
https://aclanthology.org/2014.amta-researchers.8
DOI:
Bibkey:
Cite (ACL):
Jian Zhang, Liangyou Li, Andy Way, and Qun Liu. 2014. A probabilistic feature-based fill-up for SMT. In Proceedings of the 11th Conference of the Association for Machine Translation in the Americas: MT Researchers Track, pages 96–109, Vancouver, Canada. Association for Machine Translation in the Americas.
Cite (Informal):
A probabilistic feature-based fill-up for SMT (Zhang et al., AMTA 2014)
Copy Citation:
PDF:
https://aclanthology.org/2014.amta-researchers.8.pdf