Using language and translation models to select the best among outputs from multiple MT systems

Authors:
Yasuhiro Akiba;Taro Watanabe;Eiichiro Sumita
Affiliations:
ATR Spoken Language Translation Research Laboratories, Kyoto, Japan;ATR Spoken Language Translation Research Laboratories, Kyoto, Japan;ATR Spoken Language Translation Research Laboratories, Kyoto, Japan
Venue:
COLING '02 Proceedings of the 19th international conference on Computational linguistics - Volume 1
Year:
2002

Citing 6
Cited 10

Multiple comparison procedures

Multiple comparison procedures
Machine Learning

Machine Learning
The mathematics of statistical machine translation: parameter estimation

Computational Linguistics - Special issue on using large corpora: II
Incremental translation utilizing constituent boundary patterns

COLING '96 Proceedings of the 16th conference on Computational linguistics - Volume 1
Improved statistical alignment models

ACL '00 Proceedings of the 38th Annual Meeting on Association for Computational Linguistics
Example-based machine translation using DP-matching between word sequences

DMMT '01 Proceedings of the workshop on Data-driven methods in machine translation - Volume 14

A corpus-centered approach to spoken language translation

EACL '03 Proceedings of the tenth conference on European chapter of the Association for Computational Linguistics - Volume 2
Corpus-centered computation

S2S '02 Proceedings of the ACL-02 workshop on Speech-to-speech translation: algorithms and systems - Volume 7
Multi-engine machine translation with voted language model

ACL '04 Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics
Example-based machine translation based on syntactic transfer with statistical models

COLING '04 Proceedings of the 20th international conference on Computational Linguistics
Using a mixture of N-best lists from multiple MT systems in rank-sum-based confidence measure for MT outputs

COLING '04 Proceedings of the 20th international conference on Computational Linguistics
Improving alignments for better confusion networks for combining machine translation systems

COLING '08 Proceedings of the 22nd International Conference on Computational Linguistics - Volume 1
Choosing the right translation: a syntactically informed classification approach

COLING '08 Proceedings of the 22nd International Conference on Computational Linguistics - Volume 1
Exploiting variant corpora for machine translation

NAACL-Short '06 Proceedings of the Human Language Technology Conference of the NAACL, Companion Volume: Short Papers
Multi-engine machine translation with an open-source decoder for statistical machine translation

StatMT '07 Proceedings of the Second Workshop on Statistical Machine Translation
First steps towards multi-engine machine translation

ParaText '05 Proceedings of the ACL Workshop on Building and Using Parallel Texts

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper addresses the problem of automatically selecting the best among outputs from multiple machine translation (MT) systems. Existing approaches select the output assigned the highest score according to a target language model. In some cases, the existing approaches do not work well. This paper proposes two methods to improve performance. The first method is based on a multiple comparison test and checks whether a score from language and translation models is significantly higher than the others. The second method is based on probability that a translation is not inferior to the others, which is predicted from the above scores. Experimental results show that the proposed methods achieve an improvement of 2 to 6% in performance.