Extracting Synchronous Grammar Rules From Word-Level Alignments in Linear Time

@inproceedings{Zhang2008ExtractingSG,
  title={Extracting Synchronous Grammar Rules From Word-Level Alignments in Linear Time},
  author={Hao Zhang and Daniel Gildea and David Chiang},
  booktitle={COLING},
  year={2008}
}
We generalize Uno and Yagiura’s algorithm for finding all common intervals of two permutations to the setting of two sequences with many-to-many alignment links across the two sides. We show how to maximally decompose a word-aligned sentence pair in linear time, which can be used to generate all possible phrase pairs or a Synchronous Context-Free Grammar (SCFG) with the simplest rules possible. We also use the algorithm to precisely analyze the maximum SCFG rule length needed to cover hand… CONTINUE READING
Highly Influential
This paper has highly influenced 18 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 54 citations. REVIEW CITATIONS

From This Paper

Figures, tables, results, connections, and topics extracted from this paper.
42 Extracted Citations
10 Extracted References
Similar Papers

Citing Papers

Publications influenced by this paper.
Showing 1-10 of 42 extracted citations

54 Citations

051015'09'11'13'15'17
Citations per Year
Semantic Scholar estimates that this publication has 54 citations based on the available data.

See our FAQ for additional information.

Referenced Papers

Publications referenced by this paper.
Showing 1-10 of 10 references

Revisiting T

  • Bui-Xuan, Binh Minh, Michel Habib, Christophe Paul.
  • Uno and M. Yagiura’s algorithm. In The 16th…
  • 2005
Highly Influential
5 Excerpts

What’s in a translation rule

  • Galley, Michel, Mark Hopkins, Kevin Knight, Daniel Marcu
  • In Proceedings of NAACL
  • 2004
2 Excerpts

The mathematics of statistical machine translation: Parameter estimation

  • Brown, F. Peter, Stephen A. Della Pietra, Vincent J. Della Pietra, Robert L. Mercer.
  • Computational Linguistics, 19(2):263– 311.
  • 1993
1 Excerpt

Similar Papers

Loading similar papers…