CASIA OpenIR  > 09年以前成果
Variable length language model for Chinese character recognition
Zhang, S; Wu, XL; Tan, T; Shi, YC; Gao, W
发表期刊ADVANCES IN MULTIMODAL INTERFACES - ICMI 2000, PROCEEDINGS
2000
卷号1948页码:267-271
文章类型Article
摘要We present a new type of languague model - variable length language model (VLLM) hose length is non-deterministic on the base of 5-gram combined model brought forward previously. Its main advantage lies in that it captures the function of 5-gram combined model and reflects the structural feature of every line in test text as well. Compared to previous language model, the VLLM make, use of current result to determine which kind of language model should be used next and realizes the automatic choice of language model that is constant before VLLM also resolves the problem when punctuation marks appear Based on those improvments. We make experiments and get encouraging result.
WOS标题词Science & Technology ; Technology
收录类别ISTP ; SCI
语种英语
WOS研究方向Computer Science
WOS类目Computer Science, Interdisciplinary Applications ; Computer Science, Theory & Methods
WOS记录号WOS:000174117200035
引用统计
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/9800
专题09年以前成果
作者单位Chinese Acad Sci, Inst Automat, Engn Ctr Character Recognit, Beijing 100080, Peoples R China
推荐引用方式
GB/T 7714
Zhang, S,Wu, XL,Tan, T,et al. Variable length language model for Chinese character recognition[J]. ADVANCES IN MULTIMODAL INTERFACES - ICMI 2000, PROCEEDINGS,2000,1948:267-271.
APA Zhang, S,Wu, XL,Tan, T,Shi, YC,&Gao, W.(2000).Variable length language model for Chinese character recognition.ADVANCES IN MULTIMODAL INTERFACES - ICMI 2000, PROCEEDINGS,1948,267-271.
MLA Zhang, S,et al."Variable length language model for Chinese character recognition".ADVANCES IN MULTIMODAL INTERFACES - ICMI 2000, PROCEEDINGS 1948(2000):267-271.
条目包含的文件
条目无相关文件。
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Zhang, S]的文章
[Wu, XL]的文章
[Tan, T]的文章
百度学术
百度学术中相似的文章
[Zhang, S]的文章
[Wu, XL]的文章
[Tan, T]的文章
必应学术
必应学术中相似的文章
[Zhang, S]的文章
[Wu, XL]的文章
[Tan, T]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

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。