Abstract

This paper presents a novel training algorithm for a linearly-scored block sequence translation model. The key component is a new procedure to directly optimize the global scoring function used by a SMT decoder. No translation, language, or distortion model probabilities are used as in earlier work on SMT. Therefore our method, which employs less domain specific knowledge, is both simpler and more extensible than previous approaches. Moreover, the training procedure treats the decoder as a black-box, and thus can be used to optimize any decoding scheme. The training algorithm is evaluated on a standard Arabic-English translation task. 1

Citations

992	BLEU: A Method for Automatic Evaluation of Machine Translation - Papineni, Roukos, et al. - 2002
257	A hierarchical phrase-based model for statistical machine translation - Chiang - 2005
194	Heterogeneous uncertainty sampling for supervised learning - Lewis, Catlett - 1994
156	Online large-margin training of dependency parsers - McDonald, Crammer, et al. - 2005
47	A Maximum Entropy Word Aligner for Arabic-English Machine Translation - Ittycheriah, Roukos - 2005
43	Discriminative reranking for machine translation - Shen, Sarkar, et al. - 2004
28	Local phrase reordering models for statistical machine translation - Kumar, Byrne - 2005