You are here

Self-training and co-training in biomedical word sense disambiguation.

Printer-friendly versionPrinter-friendly version
Jimeno-Yepes A, Aronson AR
BioNLP 2011 Workshop, June 2011, 182-183.
Abstract: 

Word sense disambiguation (WSD) is an intermediate task within information retrieval and information extraction, attempting to select the proper sense of ambiguous words. Due to the scarcity of training data, semi-supervised learning, which profits from seed annotated examples and a large set of unlabeled data, are worth researching. We present preliminary results of two semi-supervised learning algorithms on biomedical word sense disambiguation. Both methods add relevant  unlabeled examples to the training set, and optimal parameters are similar for each ambiguous word.

Jimeno-Yepes A, Aronson AR. Self-training and co-training in biomedical word sense disambiguation. BioNLP 2011 Workshop, June 2011, 182-183.