中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
  5. 模式分析与学习团队
Common Sense Knowledge for Handwritten Chinese Text Recognition

文献类型：期刊论文

作者Wang, Qiu-Feng1; Cambria, Erik2; Liu, Cheng-Lin1; Hussain, Amir3
刊名COGNITIVE COMPUTATION
出版日期2013-06-01
卷号5期号:2页码:234-242
关键词Common sense knowledge Natural language processing Linguistic context n-gram Handwritten Chinese text recognition
英文摘要Compared to human intelligence, computers are far short of common sense knowledge which people normally acquire during the formative years of their lives. This paper investigates the effects of employing common sense knowledge as a new linguistic context in handwritten Chinese text recognition. Three methods are introduced to supplement the standard n-gram language model: embedding model, direct model, and an ensemble of these two. The embedding model uses semantic similarities from common sense knowledge to make the n-gram probabilities estimation more reliable, especially for the unseen n-grams in the training text corpus. The direct model, in turn, considers the linguistic context of the whole document to make up for the short context limit of the n-gram model. The three models are evaluated on a large unconstrained handwriting database, CASIA-HWDB, and the results show that the adoption of common sense knowledge yields improvements in recognition performance, despite the reduced concept list hereby employed.
WOS标题词Science & Technology ; Technology ; Life Sciences & Biomedicine
类目[WOS]Computer Science, Artificial Intelligence ; Neurosciences
研究领域[WOS]Computer Science ; Neurosciences & Neurology
关键词[WOS]SPEECH RECOGNITION ; LANGUAGE MODEL ; LINE RECOGNITION ; FRAMEWORK
收录类别SCI
语种英语
WOS记录号WOS:000318648900009
源URL[http://ir.ia.ac.cn/handle/173211/3067]  
专题自动化研究所_模式识别国家重点实验室_模式分析与学习团队
作者单位1.Chinese Acad Sci, Natl Lab Pattern Recognit, Inst Automat, Beijing 100190, Peoples R China
2.Natl Univ Singapore, Temasek Labs, Singapore 117411, Singapore
3.Univ Stirling, Dept Comp Sci & Math, Stirling FK9 4LA, Scotland
推荐引用方式
GB/T 7714		 Wang, Qiu-Feng,Cambria, Erik,Liu, Cheng-Lin,et al. Common Sense Knowledge for Handwritten Chinese Text Recognition[J]. COGNITIVE COMPUTATION,2013,5(2):234-242.
APA Wang, Qiu-Feng,Cambria, Erik,Liu, Cheng-Lin,&Hussain, Amir.(2013).Common Sense Knowledge for Handwritten Chinese Text Recognition.COGNITIVE COMPUTATION,5(2),234-242.
MLA Wang, Qiu-Feng,et al."Common Sense Knowledge for Handwritten Chinese Text Recognition".COGNITIVE COMPUTATION 5.2(2013):234-242.

入库方式： OAI收割

来源：自动化研究所

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。