Abstract
We propose two statistical left-corner parsers and investigate their accuracy at varying speeds. The parser based on a generative probability model achieves state-of-the-art accuracy when sufficient time is available, but when high speed is required the parser based on a discriminative probability model performs better. Neural network probability estimation is used to handle conditioning on both the unbounded parse histories and the unbounded lookahead strings.- Anthology ID:
- W03-3011
- Volume:
- Proceedings of the Eighth International Conference on Parsing Technologies
- Month:
- April
- Year:
- 2003
- Address:
- Nancy, France
- Venue:
- IWPT
- SIG:
- SIGPARSE
- Publisher:
- Note:
- Pages:
- 115–126
- Language:
- URL:
- https://aclanthology.org/W03-3011
- DOI:
- Cite (ACL):
- James Henderson. 2003. Generative versus Discriminative Models for Statistical Left-Corner Parsing. In Proceedings of the Eighth International Conference on Parsing Technologies, pages 115–126, Nancy, France.
- Cite (Informal):
- Generative versus Discriminative Models for Statistical Left-Corner Parsing (Henderson, IWPT 2003)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/W03-3011.pdf