Informatics Report Series


Report   

EDI-INF-RR-0622


Related Pages

Report (by Number) Index
Report (by Date) Index
Author Index
Institute Index

Home
Title:A system for identifying named entities in biomedical text: how results from two evaluations reflect on both the system and the evaluations
Authors: Shipra Dingare ; Jenny Finkel ; Malvina Nissim ; Chris Manning ; Claire Grover
Date:Mar 2005
Publication Title:Comparative and Functional Genomics
Publisher:John Wiley & Sons
Publication Type:Journal Article Publication Status:Published
Volume No:6(1-2) Page Nos:77-85
DOI:10.1002/cfg.457
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 the optimal.
Links To Paper
1st Link
Bibtex format
@Article{EDI-INF-RR-0622,
author = { Shipra Dingare and Jenny Finkel and Malvina Nissim and Chris Manning and Claire Grover },
title = {A system for identifying named entities in biomedical text: how results from two evaluations reflect on both the system and the evaluations},
journal = {Comparative and Functional Genomics},
publisher = {John Wiley & Sons},
year = 2005,
month = {Mar},
volume = {6(1-2)},
pages = {77-85},
doi = {10.1002/cfg.457},
url = {http://www3.interscience.wiley.com/cgi-bin/fulltext/109932711/PDFSTART},
}


Home : Publications : Report 

Please mail <reports@inf.ed.ac.uk> with any changes or corrections.
Unless explicitly stated otherwise, all material is copyright The University of Edinburgh