Sentence-Level Quality Estimation for MT System Combination
Tsuyoshi Okita, Raphaël Rubino, Josef van Genabith · Dublin City University Open Access Institutional Repository (Dublin City University) · 2012
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.