A Bayesian model averaging method for improving SMT phrase table

Nan Duan

doi:10.1117/12.2013687

13 March 2013 A Bayesian model averaging method for improving SMT phrase table

Nan Duan

Proceedings Volume 8784, Fifth International Conference on Machine Vision (ICMV 2012): Algorithms, Pattern Recognition, and Basic Technologies; 87840F (2013) https://doi.org/10.1117/12.2013687
Event: Fifth International Conference on Machine Vision (ICMV 12), 2012, Wuhan, China

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.

Citation Download Citation

Nan Duan "A Bayesian model averaging method for improving SMT phrase table", Proc. SPIE 8784, Fifth International Conference on Machine Vision (ICMV 2012): Algorithms, Pattern Recognition, and Basic Technologies, 87840F (13 March 2013); https://doi.org/10.1117/12.2013687

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available