Incorporating linguistic structure into maximum entropy language models
文献类型:期刊论文
作者 | Fang, GL; Gao, W; Wang, ZQ |
刊名 | JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY
![]() |
出版日期 | 2003 |
卷号 | 18期号:1页码:131-136 |
关键词 | maximum entropy language model base phrase identification sign language recognition |
ISSN号 | 1000-9000 |
英文摘要 | In statistical language models, how to integrate diverse linguistic knowledge in a general framework for long-distance dependencies is a challenging issue. In this paper, an improved language model incorporating linguistic structure into maximum entropy framework is presented. The proposed model combines trigram with the structure knowledge of base phrase in which trigram is used to capture the local relation between words, while the structure knowledge of base phrase is considered to represent the long-distance relations between syntactical structures. The knowledge of syntax, semantics and vocabulary is integrated into the maximum entropy framework. Experimental results show that the proposed model improves by 24% for language model perplexity and increases about 3% for sign language recognition rate compared with the trigram model. |
WOS研究方向 | Computer Science |
语种 | 英语 |
WOS记录号 | WOS:000180577400018 |
出版者 | SCIENCE PRESS |
源URL | [http://119.78.100.204/handle/2XEOYT63/13757] ![]() |
专题 | 中国科学院计算技术研究所期刊论文_英文 |
通讯作者 | Fang, GL |
作者单位 | 1.Harbin Inst Technol, Dept Comp Sci & Engn, Harbin 150001, Peoples R China 2.Chinese Acad Sci, Comp Technol Inst, Beijing 100080, Peoples R China |
推荐引用方式 GB/T 7714 | Fang, GL,Gao, W,Wang, ZQ. Incorporating linguistic structure into maximum entropy language models[J]. JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY,2003,18(1):131-136. |
APA | Fang, GL,Gao, W,&Wang, ZQ.(2003).Incorporating linguistic structure into maximum entropy language models.JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY,18(1),131-136. |
MLA | Fang, GL,et al."Incorporating linguistic structure into maximum entropy language models".JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY 18.1(2003):131-136. |
入库方式: OAI收割
来源:计算技术研究所
浏览0
下载0
收藏0
其他版本
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。