Word Sense Disambiguation based on Maximum Entropy Classifier
Chunxiang Zhang · International Journal of Performability Engineering · 2019
Word sense disambiguation (WSD) is one of the most important research issues in the field of natural language processing.In this paper, a new method of word sense disambiguation is proposed, in which words and parts of speech (POS) are extracted as discriminative features.At the same time, a maximum entropy classifier is adopted to determine ambiguous words' semantic categories.Training data of SemEval-2007: Task#5 is used to optimize the maximum entropy model.A test corpus is applied to test the performance of the WSD classifier.Experimental results show that the performance of word sense disambiguation is improved after the proposed approach is used.