Paper: Hypothesis Mixture Decoding for Statistical Machine Translation

ACL ID P11-1126
Title Hypothesis Mixture Decoding for Statistical Machine Translation
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2011

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 o...