C4.5: programs for machine learning
C4.5: programs for machine learning
A machine learning approach to coreference resolution of noun phrases
Computational Linguistics - Special issue on computational anaphora resolution
Identifying anaphoric and non-anaphoric noun phrases to improve coreference resolution
COLING '02 Proceedings of the 19th international conference on Computational linguistics - Volume 1
A model-theoretic coreference scoring scheme
MUC6 '95 Proceedings of the 6th conference on Message understanding
Improving machine learning approaches to coreference resolution
ACL '02 Proceedings of the 40th Annual Meeting on Association for Computational Linguistics
Coreference resolution using competition learning approach
ACL '03 Proceedings of the 41st Annual Meeting on Association for Computational Linguistics - Volume 1
Using decision trees for conference resolution
IJCAI'95 Proceedings of the 14th international joint conference on Artificial intelligence - Volume 2
Global learning of noun phrase anaphoricity in coreference resolution via label propagation
EMNLP '09 Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing: Volume 2 - Volume 2
Resolving event noun phrases to their verbal mentions
EMNLP '10 Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing
A twin-candidate based approach for event pronoun resolution using composite kernel
COLING '10 Proceedings of the 23rd International Conference on Computational Linguistics
Dependency-driven anaphoricity determination for coreference resolution
COLING '10 Proceedings of the 23rd International Conference on Computational Linguistics
Learning noun phrase anaphoricity in coreference resolution via label propagation
Journal of Computer Science and Technology - Special issue on natural language processing
| Hi-index | 0.00 |
Although effective for antecedent determination, the traditional twin-candidate model can not prevent the invalid resolution of non-anaphors without additional measures. In this paper we propose a modified learning framework for the twin-candidate model. In the new framework, we make use of non-anaphors to create a special class of training instances, which leads to a classifier capable of identifying the cases of non-anaphors during resolution. In this way, the twin-candidate model itself could avoid the resolution of non-anaphors, and thus could be directly deployed to coreference resolution. The evaluation done on newswire domain shows that the twin-candidate based system with our modified framework achieves better and more reliable performance than those with other solutions.