基于多知识源的同音词识别方法  

Approaches for Recognition of Chinese Homophone Words Based on the Multiple Knowledge Sources

作　　者：宗成庆[1] 章森[1] 陈肇雄[1] 黄河燕[1] 

机构地区：[1]中科院计算所机译中心

出　　处：《中文信息学报》1998年第4期22-29,共8页Journal of Chinese Information Processing

摘　　要：本文提出了基于多知识源的同音词识别方法。该方法利用上下文条件测试函数实现了不定范围的信息相关处理，并根据词性、语义、位置、音节和词频等多种关联信息进行同音词综合识别，取得了较好的同音词识别效果。This paper presents the methods for recognition of Chinese homophone words adopted by ICP system,which is a Pinyin-Chinese characters conversion system.The methods take advantages of the context text function and realize the related information processing in indefinite range within a sentence.The part-of-speech,semantic meaning,position and the frequencies of words are all considered as the evidence to recognize the Chinese homophone words by ICP system.ICP gets a high correct ratio of recognition of homophone words.

关 键 词：音字转换 同音词识别 语音识别 多知识源 

分 类 号：TP391.42[自动化与计算机技术—计算机应用技术] TN912.34[自动化与计算机技术—计算机科学与技术]