Acquiring Sense Tagged Examples using Relevance Feedback

Supervised approaches to Word Sense Disambiguation (WSD) have been shown to outperform other approaches but are hampered by reliance on labeled training examples (the data acquisition bottleneck). This paper presents a novel approach to the automatic acquisition of labeled examples for WSD which makes use of the Information Retrieval technique of relevance feedback. This semi-supervised method generates additional labeled examples based on existing annotated data. Our approach is applied to a set of ambiguous terms from biomedical journal articles and found to significantly improve the performance of a state-of-the-art WSD system.