[1]陈静,穆志纯,孙筱倩.计算机模拟汉字字形认知过程的研究[J].智能系统学报,2008,3(3):216-221.
CHEN Jing,MU Zhi-chun,SUN Xiao-qian.Computer simulation of the cognition of Chinese characters[J].CAAI Transactions on Intelligent Systems,2008,3(3):216-221.
点击复制
CHEN Jing,MU Zhi-chun,SUN Xiao-qian.Computer simulation of the cognition of Chinese characters[J].CAAI Transactions on Intelligent Systems,2008,3(3):216-221.
计算机模拟汉字字形认知过程的研究
《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷:
3
期数:
2008年第3期
页码:
216-221
栏目:
学术论文—脑认知基础
出版日期:
2008-06-25
- Title:
- Computer simulation of the cognition of Chinese characters
- 文章编号:
- 1673-4785(2008)03-0216-06
- Keywords:
- cognitive science; artificial intelligence; Chinese characters cognition; computer simulation; self-organized model
- 分类号:
- TP391.1
- 文献标志码:
- A
- 摘要:
- 对汉字的认知研究不仅是认知科学、也是计算机科学特别是人工智能领域中的一个研究热点.但是,目前汉字认知的计算机模拟研究还相对滞后,其在认知科学研究中的作用还无法和行为实验研究等同.从认知科学的角度出发,建立汉字字形表征库,构建模型,确定训练和测试方式等,对汉字字形认知过程(学习发展历程)中汉字聚类与部件拆分意识进行了计算机模拟,以便研究汉字字形学习中的某些认知规律.通过对模型的训练与测试,得到了输入汉字的聚类效果图、部件拆分情况,以及对模型进行生字测试的结果.得出的结果能够反映某些汉字认知的规律,所以模型在一定程度上模拟了汉字字形的认知过程.
- Abstract:
- Research on the cognition of Chinese characters is a hotspot in both cognitive science and computer sci2 ence, and is an especially lively field among those investigating artificial intelligence. In sp ite of this, research u2 sing computer simulations to analyze Chinese character cognition remains relatively backward, and its value in cog2 nition studies has not been comparable with experimental research on behavior. In this paper, starting from the viewpoint of cognition science, a rep resentative database of Chinese characters was set up, a cognitive model con2 structed, and training and testing modes determined. Computer simulations were made of the clustering and sp lit2 ting of Chinese characters in the course of cognition, so that cognition rules for the percep tion of Chinese characters may be better understood. The modelwas based on a multi2layer self2organizing neural network. This training and testingmethod ensured thatwe knew how the Chinese characterswere clustered and sp lit during analysis so that the recognition of unknown words could be achieved. The research outcome suggests cognition rules for recognizing Chi2 nese characters, imp lying that the p roposed model does simulate the cognition p rocess for Chinese characters.
- 参考文献/References:
-
[1] 唐一源,张武田,马林,翁旭初,李德军,何华,贾富仓. 默读汉字词的脑功能偏侧化成像研究[J]心理学报, 2002,(04) .
?[2] 韩在柱,舒华,柏晓利,徐忠宝. 认知神经心理学的基本假设和研究方法[J]心理科学, 2002,(06) .
[3] Kangas J, Kohonen T. Developments and applications of the self -organizing map and related algorithms .Mathematics and Computers in Simulation. 1996,41, 41 :3-12 .
?[4] Li P,Farkas I,Mac Whinney B. Early lexical development in a self-organizing neural network .Neural Networks, 2004, (17) :1345 .
- 相似文献/References:
-
[1]徐心和,邓志立,王骄,等.机器博弈研究面临的各种挑战[J].智能系统学报,2008,3(4):287.
XU Xin-he,DENG Zhi-li,WANG Jiao,et al.Challenging issues facing computer game research[J].CAAI Transactions on Intelligent Systems,2008,3():287.
[2]刘宏,李哲媛,许超.视错觉现象的分类和研究进展[J].智能系统学报,2011,6(1):1.
LIU Hong,LI Zheyuan,XU Chao.The categories and research advances of visual illusions[J].CAAI Transactions on Intelligent Systems,2011,6():1.
[3]刘箴,柴艳杰.虚拟人情绪模型研究的现状和问题[J].智能系统学报,2012,7(2):95.
LIU Zhen,CHAI Yanjie.The present situation and problems with research of? a virtual human’s emotion[J].CAAI Transactions on Intelligent Systems,2012,7():95.
备注/Memo
收稿日期：2007-10-26
基金项目：北京市教委重点学科共建基金资助项目(XK100080537);; 北京语言大学规划资助项目(04GH01)
作者简介：
陈静，女，1979年生，博士研究生，主要研究方向为人工智能，模式识别。
穆志纯，男，1952年生，教授，博士生导师，主要研究方向为人工智能及其应用，模式识别，图像处理，生物特征识别，复杂系统的建模与控制，1989-1991年和1997-1999年间在英国进行访问研究，曾主持，参加国家自然科学基金项目4项，青年“863”项目1项，国家科技攻关和国际合作项目多项，并获部级科技进步二等奖1项，三等奖2项，已发表论文90余篇，其中被SCI和EI检索40余篇。
孙筱倩，女，1983年生，硕士研究生，主要研究方向问人工智能，模式识别。
通讯作者：陈静。E-mail:heart931@163.com
更新日期/Last Update:
2009-05-14