关键词: 词义消歧, 人工智能, 自然语言理解, 模式识别

Abstract: The problem of ambiguous word sense poses lots of difficulties for language automatic understanding.And the research of word sense discrimination is applied to the resolution of this problem.Statistics are booming in researching this problem.While due to limitation of the scale of training corpus，the method of statistical word sense discrimination can not attain satisfying results yet.Therefore，under condition that only limit scale corpus is available，how to improve the efficiency and effectiveness of statistical learning method is a hotspot in supervised word sense recognition research.On the basis of the idea of words extending，a new word sense discrimination method using words extending is proposed.Experiment results show that the proposed method can effectively improve the accuracy of supervised word sense discrimination as the training corpus is not enlarged.

Key words: word sense disambiguation, artificial intelligence, natural language understanding, pattern recognition