Document Classification with Word Sense Knowledge

Abstract

The performance of Word Sense Disambiguation (WSD) on a standard evaluation framework has reached an estimated upper bound. However, there is limited research on the application of WSD to relevant NLP tasks due to the high computational cost of supervised systems. In this paper, we propose a partial WSD method with sense category information and incorporate the sense knowledge into a supervised document classification framework. Experimental results show that the proposed method can constantly boost the system’s performance on document classification datasets against strong baselines.

Tasks

Reproductions