关键词: 隐喻 计算机识别 最大熵

Abstract:

Metaphor is a usual language phenomenon in our daily life,and recognizing them by the use of computers becomes a valuable research task in the fields    of natural language processing, artificial intelligence, and even applied linguistics. This paper proposes a way to recognize metaphors based on the maximum entropy model after analyzing the features of metaphor, and reasons the rationality to build a recognition model using statistical methods. The results of the experiment show that the model performs well at a high precision and recall rate, as well as the f value, thus we come to the conclusion that such a metaphor recognization model based on the maximum entropy principle is promising.

Key words: metaphor, computer recognizing, maximum entropy