句法信息指导的汉语词义消歧  

Chinese word sense disambiguation directed by syntactic information

作　　者：张春祥[1,2] 栾博[1] 高雪瑶[1] 卢志茂 

机构地区：[1]哈尔滨理工大学计算机科学与技术学院,哈尔滨150080 [2]哈尔滨理工大学软件学院,哈尔滨150080 [3]哈尔滨工程大学信息与通信工程学院,哈尔滨150001

出　　处：《计算机工程与应用》2015年第5期142-145,共4页Computer Engineering and Applications

基　　金：黑龙江省教育厅科学技术研究项目(No.12531106)

摘　　要：词义消歧要解决如何让计算机理解多义词在上下文中的具体含义,对信息检索、机器翻译、文本分类和自动文摘等自然语言处理问题有着十分重要的作用。通过引入句法信息,提出了一种新的词义消歧方法。构造歧义词汇上下文的句法树,提取句法信息、词性信息和词形信息作为消歧特征。利用贝叶斯模型来建立词义消歧分类器,并将其应用到测试数据集上。实验结果表明:消歧的准确率有所提升,达到了65%。The task of word sense disambiguation is to make computers choose the correct sense of an ambiguous word in a given context. It is important for problems in natural language processing, such as information retrieval, machine translation, text classification and automatic summarization. In this paper, a new method of word sense disambiguation is proposed, where syntactic information is introduced. The parsing tree of its context including the ambiguous word is built.Disambiguation features are extracted including parsing information, part of speech and word information. The Bayesian model is used to build word sense disambiguation classifier. Experimental results show that accuracy rate of disambiguation is improved and arrives at 65%.

关 键 词：词义消歧 句法信息 消歧特征 贝叶斯模型 

分 类 号：TP391.2[自动化与计算机技术—计算机应用技术]