tailieunhanh - Báo cáo khoa học: "Joint Decoding with Multiple Translation Models"

Current SMT systems usually decode with single translation models and cannot benefit from the strengths of other models in decoding phase. We instead propose joint decoding, a method that combines multiple translation models in one decoder. Our joint decoder draws connections among multiple models by integrating the translation hypergraphs they produce individually. Therefore, one model can share translations and even derivations with other models. Comparable to the state-of-the-art system combination technique, joint decoding achieves an absolute improvement of BLEU points over individual decoding. coding phase. . | Joint Decoding with Multiple Translation Models Yang Liu and Haitao Mi and Yang Feng and Qun Liu Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences . Box 2704 Beijing 100190 China yliu htmi fengyang liuqun @ Abstract Current SMT systems usually decode with single translation models and cannot benefit from the strengths of other models in decoding phase. We instead propose joint decoding a method that combines multiple translation models in one decoder. Our joint decoder draws connections among multiple models by integrating the translation hypergraphs they produce individually. Therefore one model can share translations and even derivations with other models. Comparable to the state-of-the-art system combination technique joint decoding achieves an absolute improvement of BLEU points over individual decoding. 1 Introduction System combination aims to find consensus translations among different machine translation systems. It proves that such consensus translations are usually better than the output of individual systems Frederking and Nirenburg 1994 . Recent several years have witnessed the rapid development of system combination methods based on confusion networks . Rosti et al. 2007 He et al. 2008 which show state-of-the-art performance in MT benchmarks. A confusion network consists of a sequence of sets of candidate words. Each candidate word is associated with a score. The optimal consensus translation can be obtained by selecting one word from each set of candidates to maximizing the overall score. While it is easy and efficient to manipulate strings current methods usually have no access to most information available in decoding phase which might be useful for obtaining further improvements. In this paper we propose a framework for combining multiple translation models directly in de coding phase. 1 Based on max-translation decoding and max-derivation decoding used in .