汉语理解动词知识库建立及其在机械设计中的应用
|
摘要
本文将汉语理解语义分析应用于机械产品设计中,通过对以汉语自然语言形式表达的用户需求进行理解和分析,并将分析结果转化成概念设计要求或设计参数,为后续设计提供支持,为用户和设计人员提供了一个良好的设计环境。
首先,根据设计领域汉语理解的特点,确定应用于产品设计的汉语理解应该采用基于知识为主的方法;其次,对现有的语义分析方法进行对比,找出各个理论的优缺点,重点介绍了格语法与概念从属理论,综合二者优点作为本文语义分析的理论基础;然后,建立了面向领域的汉语理解语义分析模型:概念——事件——名词概念的抽象模型,采用产生式规则的推理形式,建立了基于该语义模型的汉语理解系统,在该系统中,用概念和静态事件来表示领域的静态知识,通过对动态事件和动态名词的设计,合理地将静态知识和动态知识结合在一起;再者,对介词短语和介词结构在汉语语言处理中的作用做了简单说明,介词句的处理最终是为以动词为中心的语义分析服务的;最后结合实际将其应用在机械产品设计的用户需求分析领域,通过系统测试,结果比较令人满意。
This text applies Chinese nature language understanding(CNLU) semantic analysis to the mechanical product design, through understanding and analyzing to the user's needs that are expressed in the form of Chinese natural language, and transform analysis result into the designing requirement of the concept or design parameter, offer a good design environment to user and designer.
First, method based on knowledge should be adopted in the Chinese natural language understanding applied to product design domain according to the characteristic of Chinese natural language understanding in product design domain. Second, carry on the contrast to the existing semantic analytical method , find out the pluses and minuses of each theory. Especially ,introduce the case grammar and the conceptual dependency theory , synthesize but two advantages regard as theoretical foundation . then an abstract understanding process of semantic analysis of domain-oriented Chinese natural language, described in the mode :Concept-Event-Noun Concept, is set up on the base of conceptual dependency theory. The domain-oriented CNLU system is designed and implemented representing by production rules based upon the above understanding process. Due to the importance of Chinese natural language knowledge, the system emphasizes on the disposals with knowledge as follows: the static knowledge of design domain is represented by concept and static event to provide a semantic base for dynamic semantic analysis; the defined templates of dynamic event and dynamic noun designed apply reasonably static knowledge on the analysis and understanding process. Moreover, the importance of semantic analysis of prepositional phrases and structures in CNLU is illuminated briefly, totally the analysis of prepositional phrases and structures is applied to semantic analysis with verb groups as its center. Last, the semantic analysis is applied to the design of the Man-machine interface in mechanical transmission. Meanwhile, the knowledge database and some rules of semantic analysis of events are established and it runs well after debugging. It is hopeful to realize the computer-aided user requirement analysis.
首先,根据设计领域汉语理解的特点,确定应用于产品设计的汉语理解应该采用基于知识为主的方法;其次,对现有的语义分析方法进行对比,找出各个理论的优缺点,重点介绍了格语法与概念从属理论,综合二者优点作为本文语义分析的理论基础;然后,建立了面向领域的汉语理解语义分析模型:概念——事件——名词概念的抽象模型,采用产生式规则的推理形式,建立了基于该语义模型的汉语理解系统,在该系统中,用概念和静态事件来表示领域的静态知识,通过对动态事件和动态名词的设计,合理地将静态知识和动态知识结合在一起;再者,对介词短语和介词结构在汉语语言处理中的作用做了简单说明,介词句的处理最终是为以动词为中心的语义分析服务的;最后结合实际将其应用在机械产品设计的用户需求分析领域,通过系统测试,结果比较令人满意。
This text applies Chinese nature language understanding(CNLU) semantic analysis to the mechanical product design, through understanding and analyzing to the user's needs that are expressed in the form of Chinese natural language, and transform analysis result into the designing requirement of the concept or design parameter, offer a good design environment to user and designer.
First, method based on knowledge should be adopted in the Chinese natural language understanding applied to product design domain according to the characteristic of Chinese natural language understanding in product design domain. Second, carry on the contrast to the existing semantic analytical method , find out the pluses and minuses of each theory. Especially ,introduce the case grammar and the conceptual dependency theory , synthesize but two advantages regard as theoretical foundation . then an abstract understanding process of semantic analysis of domain-oriented Chinese natural language, described in the mode :Concept-Event-Noun Concept, is set up on the base of conceptual dependency theory. The domain-oriented CNLU system is designed and implemented representing by production rules based upon the above understanding process. Due to the importance of Chinese natural language knowledge, the system emphasizes on the disposals with knowledge as follows: the static knowledge of design domain is represented by concept and static event to provide a semantic base for dynamic semantic analysis; the defined templates of dynamic event and dynamic noun designed apply reasonably static knowledge on the analysis and understanding process. Moreover, the importance of semantic analysis of prepositional phrases and structures in CNLU is illuminated briefly, totally the analysis of prepositional phrases and structures is applied to semantic analysis with verb groups as its center. Last, the semantic analysis is applied to the design of the Man-machine interface in mechanical transmission. Meanwhile, the knowledge database and some rules of semantic analysis of events are established and it runs well after debugging. It is hopeful to realize the computer-aided user requirement analysis.
引文
[1] 申永胜.机械原理教程.北京:清华大学出版社.1999
[2] 檀润华.创新设计:TRIZ 发明问题解决理论.北京:机械工业出版社.2002
[3] 顾佩华.设计理论与方法学研究方面的最新进展.机械与电子.1998,第 5 期:26-31.
[4] 邱宣怀,郭可谦,吴宗泽等.机械设计.第 4 版.北京:高等教育出版社.1997.
[5] 谢友柏.概念设计的基础——获取新知识的资源.机械设计.2001,18(专集):1-4.
[6] 邵军力,张景,魏长华.人工智能基础.电子工业出版社.2000
[7] 蔡义发.自然语言理解的研究与发展.计算机应用与软件. 1992,第 7 期:1-6
[8] 赵振西,李凯,金铭源.汉语的分层理解及其知识表示.中文信息.1990,第 1 期:16-22
[9] 张亚非,范建华.自然语言处理——方法与技术.计算机应用与软件.2000,第 4期:1-15
[10] 许嘉璐.现状和设想——试论中文信息处理与现代汉语研究.中文信息学报,第15 卷第 2 期:1-7
[11] 王永庆.人工智能原理与方法.西安:西安交通大学出版社.1998
[12] 陆汝铃.人工智能(上、下册).北京:科学出版社.1996
[13] 赵铁军等.机器翻译原理.哈尔滨工业大学出版社.2000.6
[14] 徐烈炯.语义学.北京:语文出版社.1995
[15] 侯广坤,邓卫字.人工智能概论.广州:中山大学出版社.1993
[16] 王开铸.自然语言理解——计算机能思维吗.哈尔滨:哈尔滨工业大学出版社.
[17] 郭艳华,周昌乐.自然语言理解研究综述.杭州电子工业学院学报.2000,第 20卷第 1 期:26-34
[18] 何新贵主编.人工智能最新进展.清华大学出版社.1994
[19] Schank R. Conceptual Information Processing. America Elsevier Publishing Company Inc. 1975
[20] 吴蔚天.汉语计算语义学,第 1 版.电子工业出版社.1999
[21] 童頫,沈一栋.知识工程.科学出版社.1992
[22] 董振东,知网.http://www.how-net.com
[23] 张宇翔,林毓材.NKI 本体理论中一些基本关系的研究.云南:云南师范大学出版社.2002
[24] 赵克.面向并行工程的设计过程理论与实现方法研究.西安电子科技大学博士论文.1995.12
[25] 马庆株.汉语语义语法范畴问题.北京语言文化大学出版社.1998.7
[26] Philip J. Hayes and Jaime G. Carbonell. A Tutorial on Techniques and Application for Natural Language Processing. Carnegie-Mellon University. October.1983.
[27] Fillmore.C.J. The case for case. In: Bach E., Harms R.eds. Universals in Linguistic Theory. New York: Holt, Rinehart and Winston, 1968
[28] 黄友能,谭琳琳.基于特定任务域的自然语言生成系统实现方法.铁路计算机应用,2004,第 13 卷第 11 期 11-13
[29] James Allen. Natural Language Understanding. The Benjamin/Cummings Publishing Company. Inc. 1995.
[30] 史忠植.知识工程.北京:清华大学出版社,1988
[31] Nilsson.N J 著.Artificial Intelligence:A New Synthesis. 北京:机械工业出版社.2000
[32] Voutilainen A. , Padro L. . Developing a hybrid NP Parser. In: Proceeding of the 5th Conference on Applied Natural Language. 1997.80-87.
[33] 徐燕中,张付英.支持企业信息化的计算机辅助产品创新设计技术.中国制造业信息化,2003.4:51-53
[34] 王太辰.中国机械设计大典.江西科学技术出版社,2002.60-103
[35] 王大康,卢颂峰.机械设计课程设计.北京:北京工业大学出版社.2000
[36] E.丽奇.人工智能引论.广州:广东科技出版社.1986
[37] Wilks Y. and Herskovits A. An Intellgent Analyser and Generator for Natural Language,in Computa-Tional and Mathematical Linguistics,Proceedings of the International Conference on Computational Linguistics. 1973,741-767.
[38] K H Chen,H H Chen. Extracting noun phrase from large-scale texts: A hybrid approach and its automatic evaluation. In:The 32nd Annual Meeting of the Association for Computational Linguistics. Las Cruces, New Mexico. 1994
[39] K W Church. A stochastic parts program and noun phrase for unrestricted text. In: Proc of 2nd Conf on Applied Natural Language Processing. Austin, Texas. 1988. 136-143.
[40] Abney, Steven. Part-of-speech tagging and partial parsing. In: Corpus-based Methods in Language and Speech. Church, Young and Bloothooft (eds.), Kluwer Academic Publisher. 1996. 119-136.
[41] Hutchins, W.J. & Somers, H. An introduction to Machine Translation. London: Academic Press. 1992
[42] Weng,Fu-liang,Wang,Ye-yi. Introduction to Computational Linguistics. The Chinese Academy of Social Press. 1998(in Chinese).
[2] 檀润华.创新设计:TRIZ 发明问题解决理论.北京:机械工业出版社.2002
[3] 顾佩华.设计理论与方法学研究方面的最新进展.机械与电子.1998,第 5 期:26-31.
[4] 邱宣怀,郭可谦,吴宗泽等.机械设计.第 4 版.北京:高等教育出版社.1997.
[5] 谢友柏.概念设计的基础——获取新知识的资源.机械设计.2001,18(专集):1-4.
[6] 邵军力,张景,魏长华.人工智能基础.电子工业出版社.2000
[7] 蔡义发.自然语言理解的研究与发展.计算机应用与软件. 1992,第 7 期:1-6
[8] 赵振西,李凯,金铭源.汉语的分层理解及其知识表示.中文信息.1990,第 1 期:16-22
[9] 张亚非,范建华.自然语言处理——方法与技术.计算机应用与软件.2000,第 4期:1-15
[10] 许嘉璐.现状和设想——试论中文信息处理与现代汉语研究.中文信息学报,第15 卷第 2 期:1-7
[11] 王永庆.人工智能原理与方法.西安:西安交通大学出版社.1998
[12] 陆汝铃.人工智能(上、下册).北京:科学出版社.1996
[13] 赵铁军等.机器翻译原理.哈尔滨工业大学出版社.2000.6
[14] 徐烈炯.语义学.北京:语文出版社.1995
[15] 侯广坤,邓卫字.人工智能概论.广州:中山大学出版社.1993
[16] 王开铸.自然语言理解——计算机能思维吗.哈尔滨:哈尔滨工业大学出版社.
[17] 郭艳华,周昌乐.自然语言理解研究综述.杭州电子工业学院学报.2000,第 20卷第 1 期:26-34
[18] 何新贵主编.人工智能最新进展.清华大学出版社.1994
[19] Schank R. Conceptual Information Processing. America Elsevier Publishing Company Inc. 1975
[20] 吴蔚天.汉语计算语义学,第 1 版.电子工业出版社.1999
[21] 童頫,沈一栋.知识工程.科学出版社.1992
[22] 董振东,知网.http://www.how-net.com
[23] 张宇翔,林毓材.NKI 本体理论中一些基本关系的研究.云南:云南师范大学出版社.2002
[24] 赵克.面向并行工程的设计过程理论与实现方法研究.西安电子科技大学博士论文.1995.12
[25] 马庆株.汉语语义语法范畴问题.北京语言文化大学出版社.1998.7
[26] Philip J. Hayes and Jaime G. Carbonell. A Tutorial on Techniques and Application for Natural Language Processing. Carnegie-Mellon University. October.1983.
[27] Fillmore.C.J. The case for case. In: Bach E., Harms R.eds. Universals in Linguistic Theory. New York: Holt, Rinehart and Winston, 1968
[28] 黄友能,谭琳琳.基于特定任务域的自然语言生成系统实现方法.铁路计算机应用,2004,第 13 卷第 11 期 11-13
[29] James Allen. Natural Language Understanding. The Benjamin/Cummings Publishing Company. Inc. 1995.
[30] 史忠植.知识工程.北京:清华大学出版社,1988
[31] Nilsson.N J 著.Artificial Intelligence:A New Synthesis. 北京:机械工业出版社.2000
[32] Voutilainen A. , Padro L. . Developing a hybrid NP Parser. In: Proceeding of the 5th Conference on Applied Natural Language. 1997.80-87.
[33] 徐燕中,张付英.支持企业信息化的计算机辅助产品创新设计技术.中国制造业信息化,2003.4:51-53
[34] 王太辰.中国机械设计大典.江西科学技术出版社,2002.60-103
[35] 王大康,卢颂峰.机械设计课程设计.北京:北京工业大学出版社.2000
[36] E.丽奇.人工智能引论.广州:广东科技出版社.1986
[37] Wilks Y. and Herskovits A. An Intellgent Analyser and Generator for Natural Language,in Computa-Tional and Mathematical Linguistics,Proceedings of the International Conference on Computational Linguistics. 1973,741-767.
[38] K H Chen,H H Chen. Extracting noun phrase from large-scale texts: A hybrid approach and its automatic evaluation. In:The 32nd Annual Meeting of the Association for Computational Linguistics. Las Cruces, New Mexico. 1994
[39] K W Church. A stochastic parts program and noun phrase for unrestricted text. In: Proc of 2nd Conf on Applied Natural Language Processing. Austin, Texas. 1988. 136-143.
[40] Abney, Steven. Part-of-speech tagging and partial parsing. In: Corpus-based Methods in Language and Speech. Church, Young and Bloothooft (eds.), Kluwer Academic Publisher. 1996. 119-136.
[41] Hutchins, W.J. & Somers, H. An introduction to Machine Translation. London: Academic Press. 1992
[42] Weng,Fu-liang,Wang,Ye-yi. Introduction to Computational Linguistics. The Chinese Academy of Social Press. 1998(in Chinese).