Dependency Model using Posterior Context

Kiyotaka Uchimoto, Masaki Murata, Satoshi Sekine, Hitoshi Isahara


Abstract
We describe a new model for dependency structure analysis. This model learns the relationship between two phrasal units called bunsetsus as three categories; ‘between’, ‘dependent’, and ‘beyond’, and estimates the dependency likelihood by considering not only the relationship between two bunsetsus but also the relationship between the left bunsetsu and all of the bunsetsus to its right. We implemented this model based on the maximum entropy model. When using the Kyoto University corpus, the dependency accuracy of our model was 88%, which is about 1% higher than that of the conventional model using exactly the same features.
Anthology ID:
2000.iwpt-1.43
Volume:
Proceedings of the Sixth International Workshop on Parsing Technologies
Month:
February 23-25
Year:
2000
Address:
Trento, Italy
Editors:
Alberto Lavelli, John Carroll, Robert C. Berwick, Harry C. Bunt, Bob Carpenter, John Carroll, Ken Church, Mark Johnson, Aravind Joshi, Ronald Kaplan, Martin Kay, Bernard Lang, Alon Lavie, Anton Nijholt, Christer Samuelsson, Mark Steedman, Oliviero Stock, Hozumi Tanaka, Masaru Tomita, Hans Uszkoreit, K. Vijay-Shanker, David Weir, Mats Wiren
Venue:
IWPT
SIG:
SIGPARSE
Publisher:
Association for Computational Linguistics
Note:
Pages:
321–322
Language:
URL:
https://aclanthology.org/2000.iwpt-1.43
DOI:
Bibkey:
Cite (ACL):
Kiyotaka Uchimoto, Masaki Murata, Satoshi Sekine, and Hitoshi Isahara. 2000. Dependency Model using Posterior Context. In Proceedings of the Sixth International Workshop on Parsing Technologies, pages 321–322, Trento, Italy. Association for Computational Linguistics.
Cite (Informal):
Dependency Model using Posterior Context (Uchimoto et al., IWPT 2000)
Copy Citation:
PDF:
https://aclanthology.org/2000.iwpt-1.43.pdf