A New Formalization of Probabilistic GLR Parsing
Kentaro Unui, Virach Sornlertlamvanich, Hozumi Tanaka, Takenobu Tokunaga
Abstract
This paper presents a new formalization of probabilistic GLR language modeling for statistical parsing. Our model inherits its essential features from Briscoe and Carroll’s generalized probabilistic LR model, which obtains context-sensitivity by assigning a probability to each LR parsing action according to its left and right context. Briscoe and Carroll’s model, however, has a drawback in that it is not formalized in any probabilistically well-founded way, which may degrade its parsing performance. Our formulation overcomes this drawback with a few significant refinements, while maintaining all the advantages of Briscoe and Carroll’s modeling.- Anthology ID:
- 1997.iwpt-1.16
- 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:
- 123–134
- Language:
- URL:
- https://aclanthology.org/1997.iwpt-1.16
- DOI:
- Cite (ACL):
- Kentaro Unui, Virach Sornlertlamvanich, Hozumi Tanaka, and Takenobu Tokunaga. 1997. A New Formalization of Probabilistic GLR Parsing. In Proceedings of the Fifth International Workshop on Parsing Technologies, pages 123–134, Boston/Cambridge, Massachusetts, USA. Association for Computational Linguistics.
- Cite (Informal):
- A New Formalization of Probabilistic GLR Parsing (Unui et al., IWPT 1997)
- PDF:
- https://preview.aclanthology.org/auto-file-uploads/1997.iwpt-1.16.pdf