Unsupervised Word Alignment by Agreement Under ITG Constraint

  title={Unsupervised Word Alignment by Agreement Under ITG Constraint},
  author={Hidetaka Kamigaito and Akihiro Tamura and Hiroya Takamura and Manabu Okumura and Eiichiro Sumita},
We propose a novel unsupervised word alignment method that uses a constraint based on Inversion Transduction Grammar (ITG) parse trees to jointly unify two directional models. Previous agreement methods are not helpful for locating alignments with long distances because they do not use any syntactic structures. In contrast, the proposed method symmetrizes alignments in consideration of their structural coherence by using the ITG constraint softly in the posterior regularization framework… CONTINUE READING


Publications referenced by this paper.

Similar Papers

Loading similar papers…