Journal of the American Society for Information Science and Technology
SenseClusters: unsupervised clustering and labeling of similar contexts
ACLdemo '05 Proceedings of the ACL 2005 on Interactive poster and demonstration sessions
Disambiguation in the biomedical domain: The role of ambiguity type
Journal of Biomedical Informatics
Disambiguation of medline abstracts using topic models
Proceedings of the ACM fifth international workshop on Data and text mining in biomedical informatics
Knowledge-based and knowledge-lean methods combined in unsupervised word sense disambiguation
Proceedings of the 2nd ACM SIGHIT International Health Informatics Symposium
Semantic relatedness for biomedical word sense disambiguation
TextGraphs-7 '12 Workshop Proceedings of TextGraphs-7 on Graph-based Methods for Natural Language Processing
Evaluating measures of semantic similarity and relatedness to disambiguate terms in biomedical text
Journal of Biomedical Informatics
Hi-index | 0.00 |
This paper introduces an unsupervised vector approach to disambiguate words in biomedical text that can be applied to all-word disambiguation. We explore using contextual information from the Unified Medical Language System (UMLS) to describe the possible 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 conflated data from the 2005 Medline Baseline.