语义分析和结构化语言模型.PDFVIP

1000-9825/2005/16(09)1523 ©2005 Journal of Software 软 件 学 报 Vol.16, No.9 ∗ 语义分析和结构化语言模型 1+ 2 1 1 李明琴 , 李涓子 , 王作英 , 陆大纟金 1(清华大学 电子工程系,北京 100084) 2(清华大学 计算机科学与技术系,北京 100084) Semantic Analysis and Structured Language Models 1+ 2 1 1 LI Ming-Qin , LI Juan-Zi , WANG Zuo-Ying , LU Da-Jin 1(Department of Electronic Engineering, Tsinghua University, Beijing 100084, China) 2(Department of Computer Science and Technology, Tsinghua University, Beijing 100084, China) + Corresponding author: Phn: +86- 10 E-mail: lmq@, Received 2004-05-14; Accepted 2004-09-07 Li MQ, Li JZ, Wang ZY, Lu DJ. Semantic analysis and structured language models. Journal of Sof tware, 2005,16(9):1523−1533. DOI: 10.1360/jos161523 Abstract: An integrated semantic analysis system is presented, and the structured language models are proposed based on it. The semantic analysis system can automatically tag semantic class for each word and analyze the semantic dependency structure between words with the precision of 90. 85% and 75.84% respectively. In order to describe sentence structure and long-distance dependency, two kinds of structured language models are examined and analyzed. Finally, these two language models are evaluated on the task of Chinese speech recognition . Experiments show that the best semantic structured language modelheadword trigram modelachieves 0. 8% absolute error reduction and 8% relative error reduction over the trigram model. Key words: semantic analysis; dependency analysis; language model; speech recognition 摘 要: 提出了一个语义分析集成系统,并在此基础上构建了结构化的语言模型.该语义分析集成系统能够自动 分析句子中各个词的词义以及词之间的语义依存关系,达到90.85%的词义标注正确率和75.84%的语义依存结构标 注正确率.为了描述语言的结构信息和长距