Open AccessGraph Algorithms for Word Sense Disambiguation in Biomedicine
Author(s) -
Rodrigo Goulart,
Juliano De Carvalho,
Vera de Lima
Publication year - 2015
Language(s) - English
Resource type - Conference proceedings
DOI - 10.5753/sbcas.2015.10365
Subject(s) - word sense disambiguation , biomedicine , computer science , graph , natural language processing , artificial intelligence , task (project management) , word (group theory) , biomedical text mining , point (geometry) , algorithm , machine learning , theoretical computer science , text mining , mathematics , genetics , geometry , management , wordnet , economics , biology
Word Sense Disambiguation (WSD) is an important task for Biomedicine text-mining. Supervised WSD methods have the best results but they are complex and their cost for testing is too high. This work presents an experiment on WSD using graph-based approaches (unsupervised methods). Three algorithms were tested and compared to the state of the art. Results indicate that similar performance could be reached with different levels of complexity, what may point to a new approach to this problem.