Hypothesis Mixture Decoding for Statistical Machine Translation

Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics, pages 1258–1267, Portland, Oregon, June 19-24, 2011. c⃝2011 Association for Computational Linguistics Hypothesis Mixture Decoding for Statistical Machine Translation Nan Duan, Mu Li, and Ming Zhou School of Computer Science and Technology Natural Language Computing Group Tianjin University Microsoft Research Asia Tianjin, China Beijing, China v-naduan@microsoft.com {muli,mingzhou}@microsoft.com Abstract This paper presents hypothesis mixture decoding (HM decoding), a new decoding scheme that performs translation reconstruction using hypo- theses generated by multiple translation systems. HM decoding involves two decoding stages: first, each component system decodes indepen- dently, with the explored search space kept for use in the next step; second, a new search space is constructed by composing existing hypotheses produced by all component systems using a set of rules provided by the HM decoder itself, and a new set of model independent features are used to seek the final best translation from this new search space. Few assumptions are made by our approach about the underlying component systems, enabling us to leverage SMT models based on arbitrary paradigms. We compare our approach with several related techniques, and demonstrate significant BLEU improvements in large-scale Chinese-to-English translation tasks. 1 Introduction Besides tremendous efforts on constructing more complicated and accurate models for statistical machine translation (SMT) (Och and Ney, 2004; Chiang, 2005; Galley et al., 2006; Shen et al., 2008; Chiang 2010), many researchers have concentrated on the approaches that improve translation quality using information between hypotheses from one or more SMT systems as well. System combination is built on top of the N-best outputs generated by multiple component systems (Rosti et al., 2007; He et al., 2008; Li et al., 2009b) which aligns multiple hypotheses to build confu- sion networks as new search spaces, and outputs the highest scoring paths as the final translations. Consensus decoding, on the other hand, can be based on either single or multiple systems: single system based methods (Kumar and Byrne, 2004; Tromble et al., 2008; DeNero et al., 2009; Kumar et al., 2009) re-rank translations produced by a single SMT model using either n-gram posteriors or expected n-gram counts. Because hypotheses generated by a single model are highly correlated, improvements obtained are usually small; recently, dedicated efforts have been made to extend it from single system to multiple systems (Li et al., 2009a; DeNero et al., 2010; Duan et al., 2010). Such me- thods select translations by optimizing consensus models over the combined hypotheses using all component systems’ posterior distributions. Although these two types of approaches have shown consistent improvements over the standard Maximum a Posteriori (MAP) decoding scheme, most of them are implemented as post-processing procedures over translations generated by MAP decoders. In this sense, the work of Li et al. (2009a) is different in that both partial and full hypotheses are re-ranked during the decoding phase directly using consensus between translations from differ- ent SMT systems. However, their method does not change component systems’ search spaces. This paper presents hypothesis mixture decoding (HM …

Content truncated to 500 words