Learning Lexicalized Reordering Models from Reordering Graphs

@inproceedings{Su2010LearningLR,
  title={Learning Lexicalized Reordering Models from Reordering Graphs},
  author={Jinsong Su and Yang Liu and Yajuan L{\"u} and Haitao Mi and Qun Liu},
  booktitle={ACL},
  year={2010}
}
Lexicalized reordering models play a crucial role in phrase-based translation systems. They are usually learned from the word-aligned bilingual corpus by examining the reordering relations of adjacent phrases. Instead of just checking whether there is one phrase adjacent to a given phrase, we argue that it is important to take the number of adjacent phrases into account for better estimations of reordering models. We propose to use a structure named reordering graph, which represents all phrase… CONTINUE READING

Similar Papers

Loading similar papers…