Abstract
We introduce a novel parser based on a probabilistic version of a left-corner parser. The left-corner strategy is attractive because rule probabilities can be conditioned on both top-down goals and bottom-up derivations. We develop the underlying theory and explain how a grammar can be induced from analyzed data. We show that the left-corner approach provides an advantage over simple top-down probabilistic context-free grammars in parsing the Wall Street Journal using a grammar induced from the Penn Treebank. We also conclude that the Penn Treebank provides a fairly weak tes bed due to the flatness of its bracketings and to the obvious overgeneration and undergeneration of its induced grammar.- Anthology ID:
- 1997.iwpt-1.18
- Volume:
- Proceedings of the Fifth International Workshop on Parsing Technologies
- Month:
- September 17-20
- Year:
- 1997
- Address:
- Boston/Cambridge, Massachusetts, USA
- Venue:
- IWPT
- SIG:
- SIGPARSE
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 147–158
- Language:
- URL:
- https://aclanthology.org/1997.iwpt-1.18
- DOI:
- Cite (ACL):
- Christopher D. Manning and Bob Carpenter. 1997. Probabilistic Parsing using Left Corner Language Models. In Proceedings of the Fifth International Workshop on Parsing Technologies, pages 147–158, Boston/Cambridge, Massachusetts, USA. Association for Computational Linguistics.
- Cite (Informal):
- Probabilistic Parsing using Left Corner Language Models (Manning & Carpenter, IWPT 1997)
- PDF:
- https://preview.aclanthology.org/author-affiliation/1997.iwpt-1.18.pdf