Đang chuẩn bị nút TẢI XUỐNG, xin hãy chờ
Tải xuống
We present a discriminative model that directly predicts which set of phrasal translation rules should be extracted from a sentence pair. Our model scores extraction sets: nested collections of all the overlapping phrase pairs consistent with an underlying word alignment. Extraction set models provide two principle advantages over word-factored alignment models. First, we can incorporate features on phrase pairs, in addition to word links. Second, we can optimize for an extraction-based loss function that relates directly to the end task of generating translations. . | Discriminative Modeling of Extraction Sets for Machine Translation John DeNero and Dan Klein Computer Science Division University of California Berkeley denero klein @cs.berkeley.edu Abstract We present a discriminative model that directly predicts which set of phrasal translation rules should be extracted from a sentence pair. Our model scores extraction sets nested collections of all the overlapping phrase pairs consistent with an underlying word alignment. Extraction set models provide two principle advantages over word-factored alignment models. First we can incorporate features on phrase pairs in addition to word links. Second we can optimize for an extraction-based loss function that relates directly to the end task of generating translations. Our model gives improvements in alignment quality relative to state-of-the-art unsupervised and supervised baselines as well as providing up to a 1.4 improvement in BLEU score in Chinese-to-English translation experiments. 1 Introduction In the last decade the field of statistical machine translation has shifted from generating sentences word by word to systems that recycle whole fragments of training examples expressed as translation rules. This general paradigm was first pursued using contiguous phrases Och et al. 1999 Koehn et al. 2003 and has since been generalized to a wide variety of hierarchical and syntactic formalisms. The training stage of statistical systems focuses primarily on discovering translation rules in parallel corpora. Most systems discover translation rules via a two-stage pipeline a parallel corpus is aligned at the word level and then a second procedure extracts fragment-level rules from word-aligned sentence pairs. This paper offers a model-based alternative to phrasal rule extraction which merges this two-stage pipeline into a single step. We present a discriminative model that directly predicts which set of phrasal translation rules should be extracted from a sentence pair. Our model predicts