Evaluating dependency representation for event extraction

Authors:
Makoto Miwa;Sampo Pyysalo;Tadayoshi Hara;Jun'ichi Tsujii
Affiliations:
The University of Tokyo;The University of Tokyo;The University of Tokyo;The University of Tokyo and University of Manchester and National Center for Text Mining
Venue:
COLING '10 Proceedings of the 23rd International Conference on Computational Linguistics
Year:
2010

Citing 11
Cited 6

Accurate unlexicalized parsing

ACL '03 Proceedings of the 41st Annual Meeting on Association for Computational Linguistics - Volume 1
Evaluating contributions of natural language parsers to protein–protein interaction extraction

Bioinformatics
Overview of BioNLP'09 shared task on event extraction

BioNLP '09 Proceedings of the Workshop on Current Trends in Biomedical Natural Language Processing: Shared Task
Extracting complex biological events with rich graph-based feature sets

BioNLP '09 Proceedings of the Workshop on Current Trends in Biomedical Natural Language Processing: Shared Task
A Markov logic approach to bio-molecular event extraction

BioNLP '09 Proceedings of the Workshop on Current Trends in Biomedical Natural Language Processing: Shared Task
On the unification of syntactic annotations under the stanford dependency scheme: a case study on BioInfer and GENIA

BioNLP '07 Proceedings of the Workshop on BioNLP 2007: Biological, Translational, and Clinical Language Processing
Porting a lexicalized-grammar parser to the biomedical domain

Journal of Biomedical Informatics
Unbounded dependency recovery for parser evaluation

EMNLP '09 Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing: Volume 2 - Volume 2
A comparative study of syntactic parsers for event extraction

BioNLP '10 Proceedings of the 2010 Workshop on Biomedical Natural Language Processing
Any domain parsing: automatic domain adaptation for natural language parsing

Any domain parsing: automatic domain adaptation for natural language parsing
Developing a robust part-of-speech tagger for biomedical text

PCI'05 Proceedings of the 10th Panhellenic conference on Advances in Informatics

Towards exhaustive protein modification event extraction

BioNLP '11 Proceedings of BioNLP 2011 Workshop
Search-based structured prediction applied to biomedical event extraction

CoNLL '11 Proceedings of the Fifteenth Conference on Computational Natural Language Learning
Overview of the infectious diseases (ID) task of BioNLP Shared Task 2011

BioNLP Shared Task '11 Proceedings of the BioNLP Shared Task 2011 Workshop
BioNLP Shared Task 2011: supporting resources

BioNLP Shared Task '11 Proceedings of the BioNLP Shared Task 2011 Workshop
Fast and robust joint models for biomedical event extraction

EMNLP '11 Proceedings of the Conference on Empirical Methods in Natural Language Processing
Tree kernel-based protein-protein interaction extraction from biomedical literature

Journal of Biomedical Informatics

Quantified Score

Hi-index	0.00

Visualization

Abstract

The detailed analyses of sentence structure provided by parsers have been applied to address several information extraction tasks. In a recent bio-molecular event extraction task, state-of-the-art performance was achieved by systems building specifically on dependency representations of parser output. While intrinsic evaluations have shown significant advances in both general and domain-specific parsing, the question of how these translate into practical advantage is seldom considered. In this paper, we analyze how event extraction performance is affected by parser and dependency representation, further considering the relation between intrinsic evaluation and performance at the extraction task. We find that good intrinsic evaluation results do not always imply good extraction performance, and that the types and structures of different dependency representations have specific advantages and disadvantages for the event extraction task.