UCL logo

UCL Discovery

UCL home » Library Services » Electronic resources » UCL Discovery

Coreference based event extraction on biomedical text

Yoshikawa, K; Asahara, M; Hirao, T; Riedel, S; Matsumoto, Y; (2011) Coreference based event extraction on biomedical text. Transactions of the Japanese Society for Artificial Intelligence , 26 (2) 318 - 323. 10.1527/tjsai.26.318. Gold open access

Abstract

This paper presents a new approach that exploits coreference information to extract event-argument (E-A) relations from biomedical documents. This approach has two advantages: (1) it can extract a large number of valuable E-A relations for document understanding based on the concept of salience in discourse; (2) it enables us to identify cross-sentence E-A using transitivity involving coreference relations. We propose two coreference-based models: a pipeline based on an Support Vector Machine (SVM) classifier, and a jointMarkov Logic Network (MLN). We show the effectiveness of these models on GENIA Event Corpus.

Type:Article
Title:Coreference based event extraction on biomedical text
Open access status:An open access publication
DOI:10.1527/tjsai.26.318
UCL classification:UCL > School of BEAMS > Faculty of Engineering Science > Computer Science

Archive Staff Only: edit this record