Effectiveness comparison of feature words for word sense disambiguation

The context of ambiguous words is the most important clue for word sense disambiguation (WSD). The selection and weight assignment of feature words affect the performance of WSD directly. The existing method usually selects the words in a certain length of window as feature words, which is easy to induce noise words in a short distance and neglect feature words in a long distance. Syntax parsing can analyze syntactic relations among words and output phrase structure tree or dependency tree of the sentence, which could be utilized to select feature words. The paper proposes the methods to select feature words based on phrase structure tree and dependency tree, and compares their effectiveness in detail. The results of experiments show that the method to select feature words and assign their weights with dependency tree is a preferred strategy for WSD.