Loading...
Loading...

Go to the content (press return)

A global relaxation labeling approach to coreference resolution

Author
Sapena, E.; Padro, L.; Turmo, J.
Type of activity
Presentation of work at congresses
Name of edition
23rd International Conference on Computational Linguistics
Date of publication
2010
Presentation's date
2010-08
Book of congress proceedings
Proceedings of 23rd International Conference on Computational Linguistics (COLING - 2010)
First page
1086
Last page
1094
Repository
http://hdl.handle.net/2117/16255 Open in new window
http://www.aclweb.org/anthology/C10-2125 Open in new window
Abstract
This paper presents a constraint-based graph partitioning approach to coreference resolution solved by relaxation labeling. The approach combines the strengths of groupwise classifiers and chain formation methods in one global method. Experiments show that our approach significantly outperforms systems based on separate classification and chain formation steps, and that it achieves the best results in the state of the art for the same dataset and metrics.
Citation
Sapena, E.; Padró, L.; Turmo, J. A global relaxation labeling approach to coreference resolution. A: International Conference on Computational Linguistics. "Proceedings of 23rd International Conference on Computational Linguistics (COLING - 2010)". Beijing: 2010, p. 1086-1094.
Group of research
GPLN - Natural Language Processing Group
IDEAI-UPC - Intelligent Data Science and Artificial Intelligence Research Center
TALP - Centre for Language and Speech Technologies and Applications

Participants