Wide Coverage Incremental Parsing by Learning Attachment Preferences

@inproceedings{Costa2001WideCI,
  title={Wide Coverage Incremental Parsing by Learning Attachment Preferences},
  author={Fabrizio Costa and Vincenzo Lombardo and Paolo Frasconi and Giovanni Soda},
  booktitle={AI*IA},
  year={2001}
}
This paper presents a novel method for wide coverage parsing using an incremental strategy, which is psycholinguistically motivated. A recursive neural network is trained on treebank data to learn first pass attachments, and is employed as a heuristic for guiding parsing decision. The parser is lexically blind and uses beam search to explore the space of plausible partial parses and returns the full analysis having highest probability. Results are based on preliminary tests on the WSJ section… CONTINUE READING
Highly Cited
This paper has 20 citations. REVIEW CITATIONS
11 Citations
18 References
Similar Papers

References

Publications referenced by this paper.
Showing 1-10 of 18 references

Incremental pre-head attachment in japanese parsing

  • Y. Kamide, D. C. Mitchell
  • Language and Cognitive Processes,
  • 1999
1 Excerpt

Incrementality and lexicalism: A treebank study

  • V. Lombardo, P. Sturt
  • Lexical Representations in Sentence Processing…
  • 1999
1 Excerpt

A new statistical parser based on bigram lexical dependencies

  • M. Collins
  • In Proc. of 34th ACL,
  • 1996
1 Excerpt

Similar Papers

Loading similar papers…