Đang chuẩn bị nút TẢI XUỐNG, xin hãy chờ
Tải xuống
For many years, statistical machine translation relied on generative models to provide bilingual word alignments. In 2005, several independent efforts showed that discriminative models could be used to enhance or replace the standard generative approach. Building on this work, we demonstrate substantial improvement in word-alignment accuracy, partly though improved training methods, but predominantly through selection of more and better features. Our best model produces the lowest alignment error rate yet reported on Canadian Hansards bilingual data. . | Improved Discriminative Bilingual Word Alignment Robert C. Moore Wen-tau Yih Andreas Bode Microsoft Research Redmond WA 98052 USA bobmoore scottyhi abode @microsoft.com Abstract For many years statistical machine translation relied on generative models to provide bilingual word alignments. In 2005 several independent efforts showed that discriminative models could be used to enhance or replace the standard generative approach. Building on this work we demonstrate substantial improvement in word-alignment accuracy partly though improved training methods but predominantly through selection of more and better features. Our best model produces the lowest alignment error rate yet reported on Canadian Hansards bilingual data. 1 Introduction Until recently almost all work in statistical machine translation was based on word alignments obtained from combinations of generative prob-abalistic models developed at IBM by Brown et al. 1993 sometimes augmented by an HMM-based model or Och and Ney s Model 6 Och and Ney 2003 . In 2005 however several independent efforts Liu et al. 2005 Fraser and Marcu 2005 Ayan et al. 2005 Taskar et al. 2005 Moore 2005 Ittycheriah and Roukos 2005 demonstrated that discriminatively trained models can equal or surpass the alignment accuracy of the standard models if the usual unlabeled bilingual training corpus is supplemented with human-annotated word alignments for only a small subset of the training data. The work cited above makes use of various training procedures and a wide variety of features. Indeed whereas it can be difficult to design a factorization of a generative model that incorporates all the desired information it is relatively easy to add arbitrary features to a discriminative model. We take advantage of this building on our existing framework Moore 2005 to substantially reduce the alignment error rate AER we previously reported given the same training and test data. Through a careful choice of features and modest improvements in .
