Heuristics and Parse Ranking

B. Srinivas, Christine Doran, Seth Kulick


Abstract
There are currently two philosophies for building grammars and parsers – Statistically induced grammars and Wide-coverage grammars. One way to combine the strengths of both approaches is to have a wide-coverage grammar with a heuristic component which is domain independent but whose contribution is tuned to particular domains. In this paper, we discuss a three-stage approach to disambiguation in the context of a lexicalized grammar, using a variety of domain independent heuristic techniques. We present a training algorithm which uses hand-bracketed treebank parses to set the weights of these heuristics. We compare the performance of our grammar against the performance of the IBM statistical grammar, using both untrained and trained weights for the heuristics.
Anthology ID:
1995.iwpt-1.27
Volume:
Proceedings of the Fourth International Workshop on Parsing Technologies
Month:
September 20-24
Year:
1995
Address:
Prague and Karlovy Vary, Czech Republic
Editors:
Eva Hajicova, Bernard Lang, Robert Berwick, Harry Bunt, Bob Carpenter, Ken Church, Aravind Joshi, Ronald Kaplan, Martin Kay, Makoto Nagao, Anton Nijholt, Mark Steedman, Henry Thompson, Masaru Tomita, K. Vijay-Shanker, Yorick Wilks, Kent Wittenburg
Venues:
IWPT | WS
SIG:
SIGPARSE
Publisher:
Association for Computational Linguistics
Note:
Pages:
224–233
Language:
URL:
https://aclanthology.org/1995.iwpt-1.27
DOI:
Bibkey:
Cite (ACL):
B. Srinivas, Christine Doran, and Seth Kulick. 1995. Heuristics and Parse Ranking. In Proceedings of the Fourth International Workshop on Parsing Technologies, pages 224–233, Prague and Karlovy Vary, Czech Republic. Association for Computational Linguistics.
Cite (Informal):
Heuristics and Parse Ranking (Srinivas et al., IWPT-WS 1995)
Copy Citation:
PDF:
https://aclanthology.org/1995.iwpt-1.27.pdf