A Comparison of Syntactically Motivated Word Alignment Spaces

@inproceedings{Cherry2006ACO,
  title={A Comparison of Syntactically Motivated Word Alignment Spaces},
  author={Colin Cherry and Dekang Lin},
  booktitle={EACL},
  year={2006}
}
This work is concerned with the space of alignments searched by word alignment systems. We focus on situations where word re-ordering is limited by syntax. We present two new alignment spaces that limit an ITG according to a given dependency parse. We provide D-ITG grammars to search these spaces completely and without redundancy. We conduct a careful comparison of five alignment spaces, and show that limiting search with an ITG reduces error rate by 10%, while a D-ITG produces a 31% reduction. 

From This Paper

Figures, tables, results, and topics from this paper.

Key Quantitative Results

  • We conduct a careful comparison of five alignment spaces, and show that limiting search with an ITG reduces error rate by 10%, while a D-ITG produces a 31% reduction.

Similar Papers

Loading similar papers…