DMCA
Improving Statistical Machine Translation using Lexicalized Rule Selection (2008)
Cached
Download Links
| Venue: | In Proc. Coling |
| Citations: | 24 - 9 self |
BibTeX
@INPROCEEDINGS{He08improvingstatistical,
author = {Zhongjun He and Qun Liu and Shouxun Lin},
title = {Improving Statistical Machine Translation using Lexicalized Rule Selection},
booktitle = {In Proc. Coling},
year = {2008},
pages = {321328}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
This paper proposes a novel lexicalized approach for rule selection for syntax-based statistical machine translation (SMT). We build maximum entropy (MaxEnt) models which combine rich context information for selecting translation rules during decoding. We successfully integrate the MaxEnt-based rule selection models into the state-of-the-art syntax-based SMT model. Experiments show that our lexicalized approach for rule selection achieves statistically significant improvements over the state-of-the-art SMT system. 1
Keyphrases
statistical machine translation lexicalized rule selection rule selection significant improvement maximum entropy maxent-based rule selection model syntax-based statistical machine translation state-of-the-art smt system rich context information lexicalized approach novel lexicalized approach state-of-the-art syntax-based smt model translation rule
