Ensemble construction for SMT system combination via leave-one-out features

Nan Duan

doi:10.1117/12.2013686

13 March 2013 Ensemble construction for SMT system combination via leave-one-out features

Nan Duan

Proceedings Volume 8783, Fifth International Conference on Machine Vision (ICMV 2012): Computer Vision, Image Analysis and Processing; 87830K (2013) https://doi.org/10.1117/12.2013686
Event: Fifth International Conference on Machine Vision (ICMV 12), 2012, Wuhan, China

Abstract

In this paper, we present a simple and effective method to systematically derive an ensemble of Statistical Machine Translation (SMT) systems from one baseline linear SMT model for use in system combination. Each system in the resulting ensemble is based on a feature set derived from the features of the baseline model (typically a subset of it). We will discuss the principles to determine the feature sets for derived systems, and present in detail the system combination model used in our work. Evaluation is performed on the data sets for NIST 2004 and NIST 2005 Chinese-to-English SMT tasks. Experimental results show that our method can bring significant improvements to baseline systems with state-of-the-art performance.

Citation Download Citation

Nan Duan "Ensemble construction for SMT system combination via leave-one-out features", Proc. SPIE 8783, Fifth International Conference on Machine Vision (ICMV 2012): Computer Vision, Image Analysis and Processing, 87830K (13 March 2013); https://doi.org/10.1117/12.2013686

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