Using Distributed Representations to Disambiguate Biomedical and Clinical Concepts
TL
TL;DR
A knowledge-based method for Word Sense Disambiguation in the domains of biomedical and clinical text is reported, using no relational information, to obtain comparable performance to previous approaches on the MSH-WSD dataset.
Abstract
In this paper, we report a knowledge-based method for Word Sense Disambiguation in the domains of biomedical and clinical text. We combine word representations created on large corpora with a small number of definitions from the UMLS to create concept representations, which we then compare to representations of the context of ambiguous terms. Using no relational information, we obtain comparable performance to previous approaches on the MSH-WSD dataset, which is a well-known dataset in the biomedical domain. Additionally, our method is fast and easy to set up and extend to other domains. Supplementary materials, including source code, can be found at https: //github.com/clips/yarn
References23 items
1
MIMIC-III, a freely accessible critical care database
2
Deep Unordered Composition Rivals Syntactic Methods for Text Classification
3
Knowledge based word-concept model estimation and refinement for biomedical text mining.
4
A Unified Model for Word Sense Representation and Disambiguation
5