Share Email Print
cover

Proceedings Paper

A Bayesian model averaging method for improving SMT phrase table
Author(s): Nan Duan
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Previous methods on improving translation quality by employing multiple SMT models usually carry out as a second-pass decision procedure on hypotheses from multiple systems using extra features instead of using features in existing models in more depth. In this paper, we propose translation model generalization (TMG), an approach that updates probability feature values for the translation model being used based on the model itself and a set of auxiliary models, aiming to alleviate the over-estimation problem and enhance translation quality in the first-pass decoding phase. We validate our approach for translation models based on auxiliary models built by two different ways. We also introduce novel probability variance features into the log-linear models for further improvements. We conclude our approach can be developed independently and integrated into current SMT pipeline directly. We demonstrate BLEU improvements on the NIST Chinese-to-English MT tasks for single-system decodings.

Paper Details

Date Published: 13 March 2013
PDF: 6 pages
Proc. SPIE 8784, Fifth International Conference on Machine Vision (ICMV 2012): Algorithms, Pattern Recognition, and Basic Technologies, 87840F (13 March 2013); doi: 10.1117/12.2013687
Show Author Affiliations
Nan Duan, Tianjin Univ. (China)


Published in SPIE Proceedings Vol. 8784:
Fifth International Conference on Machine Vision (ICMV 2012): Algorithms, Pattern Recognition, and Basic Technologies
Yulin Wang; Liansheng Tan; Jianhong Zhou, Editor(s)

© SPIE. Terms of Use
Back to Top