DMCA
Sentence-Level Quality Estimation for MT System Combination
Cached
Download Links
| Citations: | 6 - 3 self |
BibTeX
@MISC{Okita_sentence-levelquality,
author = {Tsuyoshi Okita and Raphaël Rubino and Jose Genabith},
title = {Sentence-Level Quality Estimation for MT System Combination},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
This paper provides the system description of the Dublin City University system combination module for our participation in the system combination task in the Second Workshop on Applying Machine Learning Techniques to Optimize the Division of Labour in Hybrid MT (ML4HMT-12). We incorporated a sentence-level quality score, obtained by sentence-level Quality Estimation (QE), as meta information guiding system combination. Instead of using BLEU or (minimum average) TER, we select a backbone for the confusion network using the estimated quality score. For the Spanish-English data, our strategy improved 0.89 BLEU points absolute compared to the best single score and 0.20 BLEU points absolute compared to the standard system combination strategy.
Keyphrases
sentence-level quality estimation mt system combination bleu point second workshop applying machine learning technique system combination spanish-english data quality score minimum average sentence-level quality score meta information confusion network single score hybrid mt standard system combination strategy system combination task system description
