A system for identifying named entities in biomedical text: how results from two evaluations reflect on both the system and the evaluations: Conference Papers

Authors:
Shipra Dingare;Malvina Nissim;Jenny Finkel;Christopher Manning;Claire Grover
Affiliations:
Institute for Communicating and Collaborative Systems, University of Edinburgh 2 Buccleuch Place,, Edinburgh EH8 9LW, UK;Institute for Communicating and Collaborative Systems, University of Edinburgh 2 Buccleuch Place,, Edinburgh EH8 9LW, UK;Department of Computer Science, Stanford University, Gates Building 1A, 353 Serra Mall, Stanford CA 94305-9010, USA;Department of Computer Science, Stanford University, Gates Building 1A, 353 Serra Mall, Stanford CA 94305-9010, USA;Institute for Communicating and Collaborative Systems, University of Edinburgh 2 Buccleuch Place,, Edinburgh EH8 9LW, UK
Venue:
Comparative and Functional Genomics
Year:
2005

Citing 0
Cited 7

Tasks, topics and relevance judging for the TREC Genomics Track: five years of experience evaluating biomedical text information retrieval systems

Information Retrieval
Annotation of chemical named entities

BioNLP '07 Proceedings of the Workshop on BioNLP 2007: Biological, Translational, and Clinical Language Processing
BaseNPs that contain gene names: domain specificity and genericity

BioNLP '07 Proceedings of the Workshop on BioNLP 2007: Biological, Translational, and Clinical Language Processing
Brief Communication: Two-phase biomedical named entity recognition using CRFs

Computational Biology and Chemistry
Broad-coverage sense disambiguation and information extraction with a supersense sequence tagger

EMNLP '06 Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing
A multi-strategy approach to biological named entity recognition

Expert Systems with Applications: An International Journal
Towards a Protein-Protein Interaction information extraction system: Recognizing named entities

Knowledge-Based Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present a maximum entropy-based system for identifying named entities (NEs) in biomedical abstracts and present its performance in the only two biomedical named entity recognition (NER) comparative evaluations that have been held to date, namely BioCreative and Coling BioNLP. Our system obtained an exact match F-score of 83.2% in the BioCreative evaluation and 70.1% in the BioNLP evaluation. We discuss our system in detail, including its rich use of local features, attention to correct boundary identification, innovative use of external knowledge resources, including parsing and web searches, and rapid adaptation to new NE sets. We also discuss in depth problems with data annotation in the evaluations which caused the final performance to be lower than optimal. Copyright © 2005 John Wiley & Sons, Ltd.