Paper: Simultaneous Identification of Biomedical Named-Entity and Functional Relation Using Statistical Parsing Techniques

ACL ID N07-2041
Title Simultaneous Identification of Biomedical Named-Entity and Functional Relation Using Statistical Parsing Techniques
Venue Human Language Technologies
Session Short Paper
Year 2007
Authors

In this paper we propose a statistical pars- ing technique that simultaneously iden- tifies biomedical named-entities (NEs) and extracts subcellular localization re- lations for bacterial proteins from the text in MEDLINE articles. We build a parser that derives both syntactic and domain-dependent semantic information and achieves an F-score of 48.4% for the relation extraction task. We then propose a semi-supervised approach that incor- porates noisy automatically labeled data to improve the F-score of our parser to 83.2%. Our key contributions are: learn- ing from noisy data, and building an an- notated corpus that can benefit relation ex- traction research.