Word sense disambiguation in the clinical domain: a comparison of knowledge-rich and knowledge-poor unsupervised methods. (18th January 2014)

• Record Type: Journal Article
• Authors: Chasin, Rachel; Rumshisky, Anna; Uzuner, Ozlem; Szolovits, Peter
• Is Part Of: Journal of the American Medical Informatics Association. Volume 21:Number 5(2014:Sep.)
• Page Start: 842
• Page End: 849
• Publication Date: 2014-01-18
• Subjects: Natural Language Processing -- Medical Language Processing -- Clinical Language Processing -- Word Sense Disambiguation; Medical informatics -- Periodicals; Information Services -- Periodicals; Medical Informatics -- Periodicals; Médecine -- Informatique -- Périodiques; Informatica; Geneeskunde; Informatique médicale; Computer network resources; Electronic journals; 610.285
• DOI: 10.1136/amiajnl-2013-002133
• Languages: English
• ISSNs: 1067-5027

Abstract

Abstract: Objective To evaluate state-of-the-art unsupervised methods on the word sense disambiguation (WSD) task in the clinical domain. In particular, to compare graph-based approaches relying on a clinical knowledge base with bottom-up topic-modeling-based approaches. We investigate several enhancements to the topic-modeling techniques that use domain-specific knowledge sources. Materials and methods The graph-based methods use variations of PageRank and distance-based similarity metrics, operating over the Unified Medical Language System (UMLS). Topic-modeling methods use unlabeled data from the Multiparameter Intelligent Monitoring in Intensive Care (MIMIC II) database to derive models for each ambiguous word. We investigate the impact of using different linguistic features for topic models, including UMLS-based and syntactic features. We use a sense-tagged clinical dataset from the Mayo Clinic for evaluation. Results The topic-modeling methods achieve 66.9% accuracy on a subset of the Mayo Clinic's data, while the graph-based methods only reach the 40–50% range, with a most-frequent-sense baseline of 56.5%. Features derived from the UMLS semantic type and concept hierarchies do not produce a gain over bag-of-words features in the topic models, but identifying phrases from UMLS and using syntax does help. Discussion Although topic models outperform graph-based methods, semantic features derived from the UMLS prove too noisy to improve performance beyond bag-of-words. Conclusions Topic modeling for WSD provides superior results in the clinical domain; however, integration of knowledge remains to be effectively exploited.