An NP-cluster based approach to coreference resolution
COLING '04 Proceedings of the 20th international conference on Computational Linguistics
Bidirectional inference with the easiest-first strategy for tagging sequence data
HLT '05 Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing
Feature forest models for probabilistic hpsg parsing
Computational Linguistics
Exploring domain differences for the design of pronoun resolution systems for biomedical text
COLING '08 Proceedings of the 22nd International Conference on Computational Linguistics - Volume 1
Conundrums in noun phrase coreference resolution: making sense of the state-of-the-art
ACL '09 Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP: Volume 2 - Volume 2
Coreference resolution with reconcile
ACLShort '10 Proceedings of the ACL 2010 Conference Short Papers
Improving noun phrase coreference resolution by matching strings
IJCNLP'04 Proceedings of the First international joint conference on Natural Language Processing
Overview of BioNLP Shared Task 2011
BioNLP Shared Task '11 Proceedings of the BioNLP Shared Task 2011 Workshop
Overview of the protein coreference task in BioNLP Shared Task 2011
BioNLP Shared Task '11 Proceedings of the BioNLP Shared Task 2011 Workshop
Anaphora resolution in biomedical literature: a hybrid approach
Proceedings of the ACM Conference on Bioinformatics, Computational Biology and Biomedicine
| Hi-index | 0.00 |
To participate in the Protein Coreference section of the BioNLP 2011 Shared Task, we use Reconcile, a coreference resolution engine, by replacing some pre-processing components and adding a new mention detector. We got some improvement from training two separate classifiers for detecting anaphora and antecedent mentions. Our system yielded the highest score in the task, F-score 34.05% in partial mention, protein links, and system recall mode. We witnessed that specialized mention detection is crucial for coreference resolution in the biomedical domain.