作者: David Martinez , Timothy Baldwin
关键词:
摘要: This paper describes a method for detecting event trigger words in biomedical text based on word sense disambiguation (WSD) approach. We first investigate the applicability of existing WSD techniques to BioNLP 2009 shared task data, and find that we are able outperform traditional CRF-based approach certain word-types. On basis this finding, combine with CRF, obtain significant improvements over standalone gaining particularly recall.