Paper: An Unsupervised Vector Approach to Biomedical Term Disambiguation: Integrating UMLS and Medline

ACL ID P08-3009
Title An Unsupervised Vector Approach to Biomedical Term Disambiguation: Integrating UMLS and Medline
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2008
Authors

This paper introduces an unsupervised vector approach to disambiguate words in biomedi- cal text that can be applied to all-word dis- ambiguation. We explore using contextual information from the Uni ed Medical Lan- guage System (UMLS) to describe the pos- sible senses of a word. We experiment with automatically creating individualized stoplists to help reduce the noise in our dataset. We compare our results to SenseClusters and Humphrey et al. (2006) using the NLM-WSD dataset and with SenseClusters using con- ated data from the 2005 Medline Baseline.