汉英机器翻译中汉语上下文语境的表示与应用研究
|
摘要
本文面向汉英机器翻译，研究了汉语上下文语境的表示与应用，并将研究成果应用于汉英机译系统ICENT中。
在汉语句法分析和语义分析的基础之上，本文建立了汉语上下文语境模型CCM(Chinese Context Model，CCM)。CCM包括上下文语境知识的表示、获取和管理三个部分，构成了一个知识系统。依据上下文语境的动态变化性，CCM采用一种结构化的语义网络表示上下文语境知识，称为概念信息体关联网络CIURN(Concept Information Unit Relation Network，CIURN)，并建立了动态获取上下文语境知识以及动态地管理和维护上下文语境知识的机制。CCM具有系统性、实用性、动态性、结构性和可扩充性的特点，其上下文语境知识包含句法信息、语义信息和句子之间的连贯信息，为分析汉语句子与上下文语境的关系提供了较好的支持。CCM将汉语上下文语境知识的获取与汉语分析纳入了同一个体系，建立了一种汉语上下文语境表示与应用的基本模式。
基于汉语上下文语境模型CCM，本文研究了汉语事件时间信息的分析、主语省略句的处理和名词短语的定指性判定问题。
本文建立了汉语事件时间信息框架TIFCE(Temporal Information Frame of Chinese Event，TIFCE)，采用时制和时体两个元素描述了汉语事件的时间信息。基于CCM提出并实现了一种汉语事件时间信息分析方法，处理了汉语时间引用现象，获得了汉语事件的时间信息。该方法通过分析汉语时间短语的时间信息与时制，借助时间短语与事件之间的时间管辖关系，获得了汉语事件的时制；同时通过与汉语事件时体模板进行模式匹配获得了事件的时体。为给英语动词时态的正确生成提供信息，本文建立了汉英时间信息转换映射毛，将TIFCE中汉语事件的时间信息映射为英语动词的时态。通过对简化的新闻报道类汉语篇章语料进行实验，取得了较好的实验结果。
汉语篇章中主语省略现象给英语译文的主语以及其它句法成分的正确生成带来了许多困难，为此本文基于CCM提出并实现了一种汉语主语省略句处理方法。处理过程分为主语省略的识别和主语省略的恢复，提出了一种在汉语句子语义结构中识别主语省略的方法和一种从句法、语义和上下文语境多方面综合判断的“候选-选择”主语省略恢复策略。在实验语料中取得了较好的分析结果。
为判定汉语篇章中名词短语是否定指，为给英语译文冠词的正确生成提供信息，本文基于CCM提出并实现了一种汉语名词短语定指性判定方法。本文确立了汉语名词短语间的定指关系，提出了一种“候选-比较”汉语名词短语间定指关系建立方法，进而判定了名词短语的定指性。实验在名词短语为特指的条件下判断其定指性，验证了方法的有效性。
通过应用汉语上下文语境模型CCM及有关上下文分析方法，本文扩充了基于
国防科学技术大学研究生院学位论文
中间语言的汉英机译系统ICENT。原有系统主要以单句为对象进行句法分析和语
义分析，扩充后的ICENT系统可对汉语句子进行上下文分析，其上下文分析分为
三个子系统:时间信息分析子系统、主语省略处理子系统和名词短语定指判定子
系统，主要解决英语动词时态的生成、省略主语的确定和定冠词的添加等问题。
通过对ICENT系统原有中间语言进行扩充，在中间结构中表示了上下文分析结果，
为英语生成提供了上下文语境信息。
本文建立了汉语上下文语境模型，研究了汉语事件时间信息的分析、主语省略
句的处理以及名词短语定指性的判定问题，并基于上下文语境模型提出和实现了
相应的上下文分析方法，取得了较好的实验结果。目前，这些上下文分析方法还
只是在受限语料中进行了测试。在今后的研究工作中，我们将对汉语篇章语言现
象及其分析方法继续进行深入的研究，进一步扩大适用语料范围，提高汉英机器
翻译译文的质量。
In this thesis, we study the representation and application of Chinese context in Chinese-English machine translation, and use them in an interlingua-based Chinese-English machine translation system ICENT.
On the basis of Chinese syntactic analysis and semantic analysis, we construct a model of Chinese context, called Chinese Context Model (CCM). CCM is a knowledge system which consists of three parts: representation, acquirement and management of Chinese context knowledge. Because Chinese context is dynamic, the representation of Chinese context knowledge in CCM is a kind of structural semantic network, called Concept Information Unit Relation Network (CIURN). Moreover, the acquirement and management of Chinese context knowledge are also dynamic process in CCM. CCM has several features: systematic, practical, dynamic, structural and expandable. And the context knowledge of CCM is made up of syntactic information, semantic information and coherent information. So it is useful for Chinese analysis. In CCM, the acquirement of context knowledge is combined with Chinese analysis. It constructs a kind of basic mode of the representation and application of Chinese context.
With the context knowledge in CCM, we research on temporal information analysis of Chinese events, subject ellipsis resolution of Chinese sentences and defmiteness judgment of Chinese noun phrases.
We construct a Temporal Information Frame of Chinese Event (TIFCE) which is composed of tense and aspect of Chinese event. On the basis of CCM, an approach is proposed to analyze the temporal information of Chinese events. It resolves temporal reference in Chinese and acquires the temporal information of Chinese events. We analyze Chinese time phrases and calculate tenses of them. Then tenses of Chinese events are acquired by the tenses of time phrases. We acquire aspects of Chinese events by matching the Chinese event aspect templates. In order to get information to generate the correct English verb tense, we construct a kind of mapping relation t, to transform the temporal information in TIFCE into English verb tense. We use some simplified news reports to test our approach and get satisfied results.
It is very difficult to generate correct English sentences from those Chinese sentences that omit subjects. So we deal with the problem of subject ellipsis in Chinese sentences with the context knowledge in CCM. This process includes ellipsis subject detecting and ellipsis subject recovering. We put forward and implement a method to detect subject ellipsis in the semantic structure of a sentence, and a "candidate-selecting" strategy to recover the elliptical subject by syntactic conditions, semantic conditions and context conditions. The results of experiments are satisfied.
We propose a method to judge the defmiteness of Chinese noun phrase in order to get information to generate the definite article. We define some definite reference relations between Chinese noun phrases. Then, with the context knowledge in CCM, a "candidate-comparing" method is discussed to construct the definite reference relations
between noun phrases. Chinese noun phrases are definite when those relations have been established. We implement this method and get good results when Chinese noun phrases are specific.
With CCM and those methods discussed above, we improve the ICENT system. The original system only treats syntactic analysis and semantic analysis in one sentence. Now, ICENT system can analyze sentences with the context knowledge in CCM. ICENT has three sub-systems to process temporal information, subject ellipsis and the definiteness of Chinese noun phrase. It can deal with the problems of English verb tense generation, subject ellipsis generation and the definite article generation in Chinese-English machine translation. Moreover, the interlingua of ICENT is also improved. It enhances the representation of context information for English generation.
In summary, we construct a model of Chinese context CCM, and study temporal information of Chinese events, sub
在汉语句法分析和语义分析的基础之上，本文建立了汉语上下文语境模型CCM(Chinese Context Model，CCM)。CCM包括上下文语境知识的表示、获取和管理三个部分，构成了一个知识系统。依据上下文语境的动态变化性，CCM采用一种结构化的语义网络表示上下文语境知识，称为概念信息体关联网络CIURN(Concept Information Unit Relation Network，CIURN)，并建立了动态获取上下文语境知识以及动态地管理和维护上下文语境知识的机制。CCM具有系统性、实用性、动态性、结构性和可扩充性的特点，其上下文语境知识包含句法信息、语义信息和句子之间的连贯信息，为分析汉语句子与上下文语境的关系提供了较好的支持。CCM将汉语上下文语境知识的获取与汉语分析纳入了同一个体系，建立了一种汉语上下文语境表示与应用的基本模式。
基于汉语上下文语境模型CCM，本文研究了汉语事件时间信息的分析、主语省略句的处理和名词短语的定指性判定问题。
本文建立了汉语事件时间信息框架TIFCE(Temporal Information Frame of Chinese Event，TIFCE)，采用时制和时体两个元素描述了汉语事件的时间信息。基于CCM提出并实现了一种汉语事件时间信息分析方法，处理了汉语时间引用现象，获得了汉语事件的时间信息。该方法通过分析汉语时间短语的时间信息与时制，借助时间短语与事件之间的时间管辖关系，获得了汉语事件的时制；同时通过与汉语事件时体模板进行模式匹配获得了事件的时体。为给英语动词时态的正确生成提供信息，本文建立了汉英时间信息转换映射毛，将TIFCE中汉语事件的时间信息映射为英语动词的时态。通过对简化的新闻报道类汉语篇章语料进行实验，取得了较好的实验结果。
汉语篇章中主语省略现象给英语译文的主语以及其它句法成分的正确生成带来了许多困难，为此本文基于CCM提出并实现了一种汉语主语省略句处理方法。处理过程分为主语省略的识别和主语省略的恢复，提出了一种在汉语句子语义结构中识别主语省略的方法和一种从句法、语义和上下文语境多方面综合判断的“候选-选择”主语省略恢复策略。在实验语料中取得了较好的分析结果。
为判定汉语篇章中名词短语是否定指，为给英语译文冠词的正确生成提供信息，本文基于CCM提出并实现了一种汉语名词短语定指性判定方法。本文确立了汉语名词短语间的定指关系，提出了一种“候选-比较”汉语名词短语间定指关系建立方法，进而判定了名词短语的定指性。实验在名词短语为特指的条件下判断其定指性，验证了方法的有效性。
通过应用汉语上下文语境模型CCM及有关上下文分析方法，本文扩充了基于
国防科学技术大学研究生院学位论文
中间语言的汉英机译系统ICENT。原有系统主要以单句为对象进行句法分析和语
义分析，扩充后的ICENT系统可对汉语句子进行上下文分析，其上下文分析分为
三个子系统:时间信息分析子系统、主语省略处理子系统和名词短语定指判定子
系统，主要解决英语动词时态的生成、省略主语的确定和定冠词的添加等问题。
通过对ICENT系统原有中间语言进行扩充，在中间结构中表示了上下文分析结果，
为英语生成提供了上下文语境信息。
本文建立了汉语上下文语境模型，研究了汉语事件时间信息的分析、主语省略
句的处理以及名词短语定指性的判定问题，并基于上下文语境模型提出和实现了
相应的上下文分析方法，取得了较好的实验结果。目前，这些上下文分析方法还
只是在受限语料中进行了测试。在今后的研究工作中，我们将对汉语篇章语言现
象及其分析方法继续进行深入的研究，进一步扩大适用语料范围，提高汉英机器
翻译译文的质量。
In this thesis, we study the representation and application of Chinese context in Chinese-English machine translation, and use them in an interlingua-based Chinese-English machine translation system ICENT.
On the basis of Chinese syntactic analysis and semantic analysis, we construct a model of Chinese context, called Chinese Context Model (CCM). CCM is a knowledge system which consists of three parts: representation, acquirement and management of Chinese context knowledge. Because Chinese context is dynamic, the representation of Chinese context knowledge in CCM is a kind of structural semantic network, called Concept Information Unit Relation Network (CIURN). Moreover, the acquirement and management of Chinese context knowledge are also dynamic process in CCM. CCM has several features: systematic, practical, dynamic, structural and expandable. And the context knowledge of CCM is made up of syntactic information, semantic information and coherent information. So it is useful for Chinese analysis. In CCM, the acquirement of context knowledge is combined with Chinese analysis. It constructs a kind of basic mode of the representation and application of Chinese context.
With the context knowledge in CCM, we research on temporal information analysis of Chinese events, subject ellipsis resolution of Chinese sentences and defmiteness judgment of Chinese noun phrases.
We construct a Temporal Information Frame of Chinese Event (TIFCE) which is composed of tense and aspect of Chinese event. On the basis of CCM, an approach is proposed to analyze the temporal information of Chinese events. It resolves temporal reference in Chinese and acquires the temporal information of Chinese events. We analyze Chinese time phrases and calculate tenses of them. Then tenses of Chinese events are acquired by the tenses of time phrases. We acquire aspects of Chinese events by matching the Chinese event aspect templates. In order to get information to generate the correct English verb tense, we construct a kind of mapping relation t, to transform the temporal information in TIFCE into English verb tense. We use some simplified news reports to test our approach and get satisfied results.
It is very difficult to generate correct English sentences from those Chinese sentences that omit subjects. So we deal with the problem of subject ellipsis in Chinese sentences with the context knowledge in CCM. This process includes ellipsis subject detecting and ellipsis subject recovering. We put forward and implement a method to detect subject ellipsis in the semantic structure of a sentence, and a "candidate-selecting" strategy to recover the elliptical subject by syntactic conditions, semantic conditions and context conditions. The results of experiments are satisfied.
We propose a method to judge the defmiteness of Chinese noun phrase in order to get information to generate the definite article. We define some definite reference relations between Chinese noun phrases. Then, with the context knowledge in CCM, a "candidate-comparing" method is discussed to construct the definite reference relations
between noun phrases. Chinese noun phrases are definite when those relations have been established. We implement this method and get good results when Chinese noun phrases are specific.
With CCM and those methods discussed above, we improve the ICENT system. The original system only treats syntactic analysis and semantic analysis in one sentence. Now, ICENT system can analyze sentences with the context knowledge in CCM. ICENT has three sub-systems to process temporal information, subject ellipsis and the definiteness of Chinese noun phrase. It can deal with the problems of English verb tense generation, subject ellipsis generation and the definite article generation in Chinese-English machine translation. Moreover, the interlingua of ICENT is also improved. It enhances the representation of context information for English generation.
In summary, we construct a model of Chinese context CCM, and study temporal information of Chinese events, sub
引文
[1] Abraham, S. and Ferenc K. A theory of structural semantics. The Hague, Mouton & Co-Janua linguarum. Series minor no.49,1967
[2] Allen, J. Natural Language Understanding. The Benjamin/Cummings Publishing Company, Inc. 1995
[3 ] Barwise, J., Peerry, J. Situations and Attitudes. MIT Press, 1983
[4] Berthouzoz, C. A. Model of Context Adapted to Domain-Independent Machine Translation. In: Modeling and using context, proceedings of second international and interdisciplinary conference, CONTEXT'99, Trento, Italy, 1999, 54-66
[5] Brown, P. F. A Statistical Approach to Machine Translation. Computational Linguistics, 16(2) : 79-85
[6] Buvac, S. Resolving Lexical Ambiguity using a Formal Theory of Context. In K. Van Deemter and S. Peters (eds), Semantic Ambiguity and Underspecification. Cambridge University Press: CSLI Lecture Notes 55, 1996
[7] Carbonell, J. and Brown R. Anaphora Resloution: A Multi-Strategy Approach. In Proceedings of the International Conference on Computational Linguistics (COLING'88) . Budapest, Hungary, 1988
[8] Comrie, B. Aspect. Cambridge University Press, 1976
[9] Chafe, W. L. Meaning and the Structure of Language. Chicago: University of Chicago Press, 1970
[10] Chandious, J., Grimaila, A. 'Specialized' machine translateon. In: AMTA, 1996,206-211
[11] Chomsky, N. Deep Structure, Surface Structure, and Semantic Interpretation. In: Chomsky Noam: Studies on Semantics in Generative Grammar. Den Haag/Paris, 1972,62-119
[12] Cristea, D. An Incremental Discourse Parse Architecture. In: Natural language processing-NLP 2000, proceedings of Second International Conference, Patras, Greece, 2000 / Dimitris N. Christodoulakis (ed.). New York : Springer, 2000,162-175
[13] Dorr, B., Jordan, P., and Benoit, J. A Survey of Current Paradigms in Machine Translation. In Advances in Computers, edited by Marvin V. Zelkowitz, Vol 49, Academic Press, 1999
[14] Dowty, D. R., Wall, R. E. and Peters, S. Introduction to Montague semantics. Dordrecht, Holland: D. Reidel Pub. Co., 1981
[15] Eijck, J. and Kamp, H. Representing Discourse in Context. In Handbook of Logic and Language. Johan B. and Alice M. ed., MA: MIT Press, 1997, 178-237
[16] Erhard, W. H. Tense, Quantifiers, And Contexts. Computational Linguistics. v14,no2, 1988,3-14
[17] Fillmore, C. J. The Case for Case. In: Bach E, Harms R eds. Universals in Linguistic Theory. New York: Holt, Rinehart and Winston, 1968
[18] Fillmore, C. J. and D. Terence Langendoen. (eds.). Studies in linguistic semantics. New York: Holt, 1971
[19] Gagonon, M. and Lapalme, G From Conceptal Time to Linguistic Time. Association for Computational Linguistics, 1996． 91-127
[20] Ge, Niyu, Hale, J., Charniak, E. A statistical approach to anaphora resolution. In: Proc 6th Workshop on Very Large Corpora (COLING-ACL'98) . Montreal, Canada, 1998． 161-170
[21] Groenendijk, J. and Stokhof, M. Dynamic Predicate Logic. In Linguistics and Philosophy, 1991, vol.14． 39-100
[22] Halliday, M. A. K. and Hasan, R. Cohesion in English. London: Longman, 1976
[23] Halliday, M. A. K. Systemic Grammar and the Concept of a "Science of Language", 语言，语篇，语境，朱永生主编，北京：清华大学出版社， 1993, 1-22
[24] Heim I. The Semantics of Definites and Indefinites. Doctoral Dissertation. Unversity of Massachusetts, Amherst, 1982
[25] Hodgson, J. P. E. Knowledge representation and language in AI. New York : E. Horwood, 1991
[26] Hutchins, J. Latest Development in MT Technology: Beginning A New Era in MT Research. MT Summit IV, Kobe, Japan, 1993
[27] Hutchins, J. The Development and Use of Machine Translation Systems and Computer-based Translation Tools. Journal of Chinese Information Processing, 13(6) , 1999, 1-13
[28] http://www.lim.nl/japan.html
[29] http://www.lti.cs.cmu.edu/Research/Kant/kantoo-overview.html
[30] http://www.umiacs.umd.edu/-resnik/chinese_mt
[31] Johan, B. and Alice, M. Handbook of Logic and Language. MIT Press, 1997
[32] Kontos J., Malagardi, I., Alexandris C., Maria Bouligaraki. Greek Verb Semantic Processing for Stock Market Text Mining. In: Natural language processing-NLP 2000, proceedings of Second International Conference, Patras, Greece, 2000 / Dimitris N. Christodoulakis (ed.). New York : Springer, 2000, 395-405
[33] Liu, Xiaohu, Li, Sheng, Zhao, Tiejun, Lu Gan. Anaphora Resolution in Chinese-English Machine Translation. Proceeings of the Seventeenth International Coference on Computer Processing of Oriental Language, 1997, 537-541
[34] Lonsdale, D. W., Franz, A. M. and Leavitt, J. R. R. Large-Scale Machine Translation: An Interlingua Approach. In Proceedings of the Seventh
International Conference on Industrial and Engineering Applications of Artificial Intelligence and Expert Systems, Austin, Texas, 1994, 525-530
[35] Lyons, J. Semantics Two. Cambridge University Press, 1977
[36] Marcu, D. The rhetorical parsing, summarization, and generation of natural language texts [Ph. D. Thesis]. Department of Computer Science, University of Toronto, 1997
[37] Masaki Marata. Anaphora Resolution in Japanese Sentences Using Surface Expressions and Examples. arXiv:cs.cL/009011 v1 19 Sep 2002． http: ://www.lanl.gov/cmp-lg/
[38] Matsuoka, M. and Nagao, M. Indirect reference in Japanese sentences Discourse Anaphora and Anaphor Resolution Colloquium, Lancaster University, 1996
[39] Miikkulainen, R. Text and Discourse Understanding: The DISCERN System. Handbool of Natural Language Processing, Rober Dale, Hermann Moisl, Harold Somers (ed.), Marcel Dekker, Inc., 2000, 905-919
[40] Minsky, M. A Framework for Representing Knowledge. In The Psychology of Computer Vision, Patrick Winston, ed., McGraw-Hill, 1975,211-217
[41] McEnery, T., Wilson, A. Corpus Linguistics, Edinburgh University Press, 1996
[42] Nagao, M. A Framework of a Machine Translation between Japanese and English by Analogy Principle. Artificial and Human Intelligence, Amsterdam, Netherlands, 1984． 173-180
[43] Nilsson, N. Artificial Intelligence, A New Synthesis, China Machine Press, 1999
[44] Ono, K., Sumita, K., Miike, K. Abstract generation basd on rhetorical structure extraction. In: Proceedings of the International Conference on Computational Linguistics (Coling'94) . Kyoto: Kyoto University, 1994, 344-348
[45] Partee, B. H. The Development of Formal Semantics in Linguistic Theory. In The Handbook of Contemporary Semantic Theory, Shalom Lappin, ed., Foreign Language Teaching and Reserrch Press, 2001,11-38
[46] Rebecca, J. Passonneau. A Computational Model Of The Semantics Of Tense And Aspect. Computational Linguistics, vol 14, no.2,1988
[47] Salton, G and McGill, M. J. Introduction to Modern Information Retrieval. McGraw-Hill, 1983
[48] Suri, L. Z., McCoy, K. F., DeCristofaro, J D. A methodology for extending focusing frameworks. Computational Linguistics, 1999,25(2) : 173-194
[49] Sowa, J. (ed.). Principles of Semantic Networks. San Francisco: Morgan Kaufmann, 1991
[50] Tetreault, J. R. Analysis of syntax-based pronominal resolution. In: Proc 37th Annual Meeting of the Association for Computational Linguistics, San Francisco, 1999． 602-605
[51] Tomita, M. An Efficient Augmented-Context-Free Parsing Algorithm. Computational Linguistics, 1987,13(1-2)
[52] Voss, C. and Dorr, B. Toward a Lexicalized Grammar for Interlinguas.
Machine Translation, 1995, 10(1-2): 139-180
[53] Walker, M. A. Centering, anaphora resolution, and discourse structure. Centering in Discourse, Oxford University Press, 1998
[54] Webber, B. L. Tense As Discourse Anaphor. Computational Linguistics, vol 14, no.2, 1988
[55] Yang, Erhong. The Research of Word Sense Disambiguation Method Based on Co-occurrence Frequency of HowNet, ACL Proceedings of the Second Chinese Language Processing Workshop. 2000
[56] Yang, J. and Lange, E. SYSTRAN on AltaVista: a user study on real-time machine translation on the Inernet. In: AMTA, 1998, 275-285
[57] Yao, Tianshun, Li, Mu and Gao, Weijun. E-Chunk Based Machine Translation in CETRAN, Proceedings of International Comference on Chinese Language Computing, Chicago, USA, July 8-9, 2000
[58] 薄冰．英语时态祥解．北京：商务印书馆，1999
[59] 常宝宝，刘颖，刘群．汉英机器翻译中的冠词处理研究．中文信息学报，1998，12(3)，8-13
[60] 陈脑冲．论“主语”．外语教学与研究，1993(4)，1-9
[61] 陈平．汉语零形回指的话语分析．中国语文，1987(5)，363-378
[62] 陈平．论现代汉语时间的三元结构．中国语文，1988(6)，401-422
[63] 陈平．释汉语中名词性成分相关的回指概念．见：现代语言学研究理论、方法与事实．重庆：重庆出版社，1991
[64] 谌志群，周昌乐，郑洪．汉语语篇中人称指代消歧研究．江西师范大学学报(自然科学版)，1998，22(增刊)，133-136
[65] 陈群秀．信息处理用现代汉语语义分类词典的设计与实现．中国中文信息学会二十周年学术会议．北京：清华大学出版社，2001，148-155
[66] 陈肇雄，黄河燕．多语机器翻译及其系列应用系统研究进展．中国中文信息学会二十周年学术会议．北京：清华大学出版社，2001，66-73
[67] 程节华，杨思春，陈家骏，王启祥．汉英机器翻译中汉语的时态分析．第八届全国青年计算机学术会议．南京大学，2000
[68] 董振东，董强．机译研究中的一些误区—从译文质量分析看．自然语言理解与机器翻译，黄昌宁，张普主编，北京：清华大学出版社，2001，462-471
[69] 董振东．知网．http://www.keenage.com
[70] 冯志伟．自然语言机器翻译新论．北京：语文出版社，1994
[71] 冯志伟．自然语言的计算机处理．上海：上海外语教育出版社，1996
[72] 冯广艺．语境适应论．武汉：湖北教育出版社，1999
[73] 郭宏蕾，姚天顺．时间语义层次结构及理解．中文信息学报，1997，11(1)，11-19
[74] 龚千炎．汉语的时相时制时态．北京：商务印书馆，1995
[75] 胡壮麟．语篇的衔接与连贯．上海：上海外语教育出版社，1994
[76] 黄昌宁，李涓子．语料库语言学．北京：商务印书馆，2002
[77] 黄国文．语篇分析的理论与实践—广告语篇研究．上海：上海外语教育出版社，2001
[78] 黄曾阳．HNC(概念层次网络)理论．北京：清华大学出版社，1998
[79] 计算机科学技术百科全书．北京：清华大学出版社，1998
[80] 靳光瑾．现代汉语动词语义计算理论．北京：北京大学出版社，2001
[81] 乐眉云．Cohension and the Teaching of EFL Reading，语言．语篇．语境．朱永生主编，北京：清华大学出版社，1993，205-224
[82] 李涓子，黄昌宁，杨尔弘．一种自组织的汉语词义排歧方法．中文信息学报，1999，13(3)，1-8
[83] 廖秋忠．现代汉语中动词支配成分的省略．中国语文，1984(4)，241-247
[84] 廖秋忠．现代汉语篇章中指同的表达．中国语文，1986(2)，88-96
[85] 廖秋忠．篇章中的管界问题．中国语文，1987(4)，250-261
[86] 廖秋忠．篇章与语用和句法研究．廖秋忠文集．北京：北京语言学院出版社，1992，181-207
[87] 林杏光．现代汉语辞海．北京：人民中国出版社，1994
[88] 刘群，俞士汶．汉英机器翻译的难点分析．1998中文信息处理国际会议论文集，黄昌宁主编，北京：清华大学出版社，1998，507-514
[89] 刘海军，黄河燕，陈肇雄，智能机器翻译系统中的语境处理．计算机研究与发展，1998(4)，353-357
[90] 刘东立，唐泓英，王宝库，姚天顺．汉语分析的语义网络表示法．中文信息学报，1992，6(4)，1-10
[91] 陆俭明．现代汉语时间词说略．语言教学与研究，1991(1)，25-37
[92] 罗选民．论翻译的转换单位．外语教学与研究，1992(4)，34-40
[93] 罗选民．话语分析的英汉与比较研究．长沙：湖南人民出版社，2001
[94] 陆汝钤．人工智能(下)．北京：科学出版社，1996
[95] 陆汝占，高峰，陈玉泉，靳光瑾．汉语内涵逻辑及其应用．中国中文信息学会二十周年学术会议．北京：清华大学出版社，2001，89-95
[96] 鲁川．汉语的意合网络．语言文字应用，1998，23-29
[97] 马红妹，王挺，陈火旺．汉英机器翻译中语境知识的表示与应用．自然语言理解与机器翻译，黄昌宁，张普主编，北京：清华大学出版社，2001，278-284
[98] 马红妹，齐璇，王挺，陈火旺．汉英机器翻译中汉语篇章时间信息系统模型．计算机工程与科学，2002(4)
[99] 马红妹，王挺，陈火旺．汉语篇章时间短语的分析与时制验算．计算机研究与发展．2002(10)
[100] 马红妹，王挺，陈火旺．汉英机器翻译中主语省略句的处理．第一界学生计算语言学研讨会，北京大学，2002，203-208
[101] 马红妹，齐璇，王挺，陈火旺．汉语篇章中无标指同表达式的指称消解．计算机研究与发展．2002(增刊)
[102]麻志毅，林鸿飞，姚天顺．基于情境的文本中时间信息分析．东北大学学报(自然科学版)，1999，20(3)，239-242
[103]梅家驹．同义词词林．上海：上海辞书出版社，1996
[104]潘文国．汉英语对比纲要．北京：北京语言文化大学出版社，1997
[105]齐璇，陈火旺．ICENT汉英机译系统中的语义模型．计算机科学，2002，29(1)，44-46
[106]齐璇．汉语语义知识的表示及其在汉英机译中的应用．博士学位论文，国防科大研究生院，2002
[107]瞿宗德．汉语中主语隐现句及其英译．上海海运学院学报，1997，18(2)，106-114
[108]史晓东．Machine Translation-A Practitioner's Approach．博士学位论文，国防科学技术大学研究生院，1994
[109]史忠植．知识发现．北京：清华大学出版社，2002
[110]宋柔．汉语叙述文中的小句前部省略现象初析．中文信息学报，1992，6(3)，62-68
[111]王厚峰．汉语省略的判定于恢复研究．HNC与语言学研究．武汉：武汉理工大学出版社，2001，236-241
[112]王厚峰，何婷婷．汉语中人称代词的消解研究．计算机学报，2001，24(2)，136-143
[113]王建平．语境研究的历史与现状．语境研究论文集／(日)西殑光正编．北京：北京语言学院出版社，1992，6-25
[114]王挺．面向机器翻译的语料加工和知识获取的研究．博士学位论文，国防科学技术大学研究生院，1997
[115]王寅．语义理论与语言教学．上海：上海外语教育出版社，2001
[116]吴立德．大规模中文文本处理．上海：复旦大学出版社，1997
[117]吴鹤龄，崔林．ACM图灵奖(1966～1999)：计算机发展史的缩影．北京：高等教育出版社，2000
[118]吴为章，田小琳．汉语句群．北京：商务印书馆，2000
[119]徐赳赳．话语分析二十年．外语教学与研究，1995(1)，14-20
[120]薛翠芳，李晓黎，郭炳炎．汉语文摘系统中文本结构的自动分析．语言工程．陈力为，袁琦主编．北京：清华大学出版社，1997，332-337
[121]俞士汶等．现代汉语语法信息词典详解．北京：清华大学出版社，1998
[122]俞士汶．计算语言学的应用研究与基础研究．中国中文信息学会二十周年学术会议．北京：清华大学出版社，2001，54-65
[123]语言学百科词典．上海：上海辞书出版社，1993
[124]张益民，陆汝占，沈李斌．一种混合型的汉语篇章结构自动分析方法．软件学报，2000，11(11)，1527-1533
[125]赵铁军．汉英双向机器翻译中基于模式方法与混合策略的研究．博士学
位论文，哈尔滨工业大学，1998
[126]赵铁军，李生，孟遥，黄玉，杨沐昀．机器翻译系统中句法分析技术的研究实践．中国中文信息学会二十周年学术会议．北京：清华大学出版社，2001，249-257
[127]赵世开．汉英对比语法论集．上海：上海外语教育出版社，1999
[128]郑杰，茅于杭，董清富．基于语境的语义排歧方法．中文信息学报，2000(5)，1-7
[129]周会平，王挺，陈火旺．用LR算法分析汉语的语法关系．软件学报，1999(9)
[130]周会平．基于中间语言的汉英翻译系统ICENT的研究与实现，博士学位论文，国防科学技术大学研究生院，1999
[131]周强，詹卫东，任海波．构建大规模的汉语语块库．自然语言理解与机器翻译，黄昌宁，张普主编，北京：清华大学出版社，2001，102-115
[132]邹崇理．自然语言逻辑研究．北京：北京大学出版社，2000
[2] Allen, J. Natural Language Understanding. The Benjamin/Cummings Publishing Company, Inc. 1995
[3 ] Barwise, J., Peerry, J. Situations and Attitudes. MIT Press, 1983
[4] Berthouzoz, C. A. Model of Context Adapted to Domain-Independent Machine Translation. In: Modeling and using context, proceedings of second international and interdisciplinary conference, CONTEXT'99, Trento, Italy, 1999, 54-66
[5] Brown, P. F. A Statistical Approach to Machine Translation. Computational Linguistics, 16(2) : 79-85
[6] Buvac, S. Resolving Lexical Ambiguity using a Formal Theory of Context. In K. Van Deemter and S. Peters (eds), Semantic Ambiguity and Underspecification. Cambridge University Press: CSLI Lecture Notes 55, 1996
[7] Carbonell, J. and Brown R. Anaphora Resloution: A Multi-Strategy Approach. In Proceedings of the International Conference on Computational Linguistics (COLING'88) . Budapest, Hungary, 1988
[8] Comrie, B. Aspect. Cambridge University Press, 1976
[9] Chafe, W. L. Meaning and the Structure of Language. Chicago: University of Chicago Press, 1970
[10] Chandious, J., Grimaila, A. 'Specialized' machine translateon. In: AMTA, 1996,206-211
[11] Chomsky, N. Deep Structure, Surface Structure, and Semantic Interpretation. In: Chomsky Noam: Studies on Semantics in Generative Grammar. Den Haag/Paris, 1972,62-119
[12] Cristea, D. An Incremental Discourse Parse Architecture. In: Natural language processing-NLP 2000, proceedings of Second International Conference, Patras, Greece, 2000 / Dimitris N. Christodoulakis (ed.). New York : Springer, 2000,162-175
[13] Dorr, B., Jordan, P., and Benoit, J. A Survey of Current Paradigms in Machine Translation. In Advances in Computers, edited by Marvin V. Zelkowitz, Vol 49, Academic Press, 1999
[14] Dowty, D. R., Wall, R. E. and Peters, S. Introduction to Montague semantics. Dordrecht, Holland: D. Reidel Pub. Co., 1981
[15] Eijck, J. and Kamp, H. Representing Discourse in Context. In Handbook of Logic and Language. Johan B. and Alice M. ed., MA: MIT Press, 1997, 178-237
[16] Erhard, W. H. Tense, Quantifiers, And Contexts. Computational Linguistics. v14,no2, 1988,3-14
[17] Fillmore, C. J. The Case for Case. In: Bach E, Harms R eds. Universals in Linguistic Theory. New York: Holt, Rinehart and Winston, 1968
[18] Fillmore, C. J. and D. Terence Langendoen. (eds.). Studies in linguistic semantics. New York: Holt, 1971
[19] Gagonon, M. and Lapalme, G From Conceptal Time to Linguistic Time. Association for Computational Linguistics, 1996． 91-127
[20] Ge, Niyu, Hale, J., Charniak, E. A statistical approach to anaphora resolution. In: Proc 6th Workshop on Very Large Corpora (COLING-ACL'98) . Montreal, Canada, 1998． 161-170
[21] Groenendijk, J. and Stokhof, M. Dynamic Predicate Logic. In Linguistics and Philosophy, 1991, vol.14． 39-100
[22] Halliday, M. A. K. and Hasan, R. Cohesion in English. London: Longman, 1976
[23] Halliday, M. A. K. Systemic Grammar and the Concept of a "Science of Language", 语言，语篇，语境，朱永生主编，北京：清华大学出版社， 1993, 1-22
[24] Heim I. The Semantics of Definites and Indefinites. Doctoral Dissertation. Unversity of Massachusetts, Amherst, 1982
[25] Hodgson, J. P. E. Knowledge representation and language in AI. New York : E. Horwood, 1991
[26] Hutchins, J. Latest Development in MT Technology: Beginning A New Era in MT Research. MT Summit IV, Kobe, Japan, 1993
[27] Hutchins, J. The Development and Use of Machine Translation Systems and Computer-based Translation Tools. Journal of Chinese Information Processing, 13(6) , 1999, 1-13
[28] http://www.lim.nl/japan.html
[29] http://www.lti.cs.cmu.edu/Research/Kant/kantoo-overview.html
[30] http://www.umiacs.umd.edu/-resnik/chinese_mt
[31] Johan, B. and Alice, M. Handbook of Logic and Language. MIT Press, 1997
[32] Kontos J., Malagardi, I., Alexandris C., Maria Bouligaraki. Greek Verb Semantic Processing for Stock Market Text Mining. In: Natural language processing-NLP 2000, proceedings of Second International Conference, Patras, Greece, 2000 / Dimitris N. Christodoulakis (ed.). New York : Springer, 2000, 395-405
[33] Liu, Xiaohu, Li, Sheng, Zhao, Tiejun, Lu Gan. Anaphora Resolution in Chinese-English Machine Translation. Proceeings of the Seventeenth International Coference on Computer Processing of Oriental Language, 1997, 537-541
[34] Lonsdale, D. W., Franz, A. M. and Leavitt, J. R. R. Large-Scale Machine Translation: An Interlingua Approach. In Proceedings of the Seventh
International Conference on Industrial and Engineering Applications of Artificial Intelligence and Expert Systems, Austin, Texas, 1994, 525-530
[35] Lyons, J. Semantics Two. Cambridge University Press, 1977
[36] Marcu, D. The rhetorical parsing, summarization, and generation of natural language texts [Ph. D. Thesis]. Department of Computer Science, University of Toronto, 1997
[37] Masaki Marata. Anaphora Resolution in Japanese Sentences Using Surface Expressions and Examples. arXiv:cs.cL/009011 v1 19 Sep 2002． http: ://www.lanl.gov/cmp-lg/
[38] Matsuoka, M. and Nagao, M. Indirect reference in Japanese sentences Discourse Anaphora and Anaphor Resolution Colloquium, Lancaster University, 1996
[39] Miikkulainen, R. Text and Discourse Understanding: The DISCERN System. Handbool of Natural Language Processing, Rober Dale, Hermann Moisl, Harold Somers (ed.), Marcel Dekker, Inc., 2000, 905-919
[40] Minsky, M. A Framework for Representing Knowledge. In The Psychology of Computer Vision, Patrick Winston, ed., McGraw-Hill, 1975,211-217
[41] McEnery, T., Wilson, A. Corpus Linguistics, Edinburgh University Press, 1996
[42] Nagao, M. A Framework of a Machine Translation between Japanese and English by Analogy Principle. Artificial and Human Intelligence, Amsterdam, Netherlands, 1984． 173-180
[43] Nilsson, N. Artificial Intelligence, A New Synthesis, China Machine Press, 1999
[44] Ono, K., Sumita, K., Miike, K. Abstract generation basd on rhetorical structure extraction. In: Proceedings of the International Conference on Computational Linguistics (Coling'94) . Kyoto: Kyoto University, 1994, 344-348
[45] Partee, B. H. The Development of Formal Semantics in Linguistic Theory. In The Handbook of Contemporary Semantic Theory, Shalom Lappin, ed., Foreign Language Teaching and Reserrch Press, 2001,11-38
[46] Rebecca, J. Passonneau. A Computational Model Of The Semantics Of Tense And Aspect. Computational Linguistics, vol 14, no.2,1988
[47] Salton, G and McGill, M. J. Introduction to Modern Information Retrieval. McGraw-Hill, 1983
[48] Suri, L. Z., McCoy, K. F., DeCristofaro, J D. A methodology for extending focusing frameworks. Computational Linguistics, 1999,25(2) : 173-194
[49] Sowa, J. (ed.). Principles of Semantic Networks. San Francisco: Morgan Kaufmann, 1991
[50] Tetreault, J. R. Analysis of syntax-based pronominal resolution. In: Proc 37th Annual Meeting of the Association for Computational Linguistics, San Francisco, 1999． 602-605
[51] Tomita, M. An Efficient Augmented-Context-Free Parsing Algorithm. Computational Linguistics, 1987,13(1-2)
[52] Voss, C. and Dorr, B. Toward a Lexicalized Grammar for Interlinguas.
Machine Translation, 1995, 10(1-2): 139-180
[53] Walker, M. A. Centering, anaphora resolution, and discourse structure. Centering in Discourse, Oxford University Press, 1998
[54] Webber, B. L. Tense As Discourse Anaphor. Computational Linguistics, vol 14, no.2, 1988
[55] Yang, Erhong. The Research of Word Sense Disambiguation Method Based on Co-occurrence Frequency of HowNet, ACL Proceedings of the Second Chinese Language Processing Workshop. 2000
[56] Yang, J. and Lange, E. SYSTRAN on AltaVista: a user study on real-time machine translation on the Inernet. In: AMTA, 1998, 275-285
[57] Yao, Tianshun, Li, Mu and Gao, Weijun. E-Chunk Based Machine Translation in CETRAN, Proceedings of International Comference on Chinese Language Computing, Chicago, USA, July 8-9, 2000
[58] 薄冰．英语时态祥解．北京：商务印书馆，1999
[59] 常宝宝，刘颖，刘群．汉英机器翻译中的冠词处理研究．中文信息学报，1998，12(3)，8-13
[60] 陈脑冲．论“主语”．外语教学与研究，1993(4)，1-9
[61] 陈平．汉语零形回指的话语分析．中国语文，1987(5)，363-378
[62] 陈平．论现代汉语时间的三元结构．中国语文，1988(6)，401-422
[63] 陈平．释汉语中名词性成分相关的回指概念．见：现代语言学研究理论、方法与事实．重庆：重庆出版社，1991
[64] 谌志群，周昌乐，郑洪．汉语语篇中人称指代消歧研究．江西师范大学学报(自然科学版)，1998，22(增刊)，133-136
[65] 陈群秀．信息处理用现代汉语语义分类词典的设计与实现．中国中文信息学会二十周年学术会议．北京：清华大学出版社，2001，148-155
[66] 陈肇雄，黄河燕．多语机器翻译及其系列应用系统研究进展．中国中文信息学会二十周年学术会议．北京：清华大学出版社，2001，66-73
[67] 程节华，杨思春，陈家骏，王启祥．汉英机器翻译中汉语的时态分析．第八届全国青年计算机学术会议．南京大学，2000
[68] 董振东，董强．机译研究中的一些误区—从译文质量分析看．自然语言理解与机器翻译，黄昌宁，张普主编，北京：清华大学出版社，2001，462-471
[69] 董振东．知网．http://www.keenage.com
[70] 冯志伟．自然语言机器翻译新论．北京：语文出版社，1994
[71] 冯志伟．自然语言的计算机处理．上海：上海外语教育出版社，1996
[72] 冯广艺．语境适应论．武汉：湖北教育出版社，1999
[73] 郭宏蕾，姚天顺．时间语义层次结构及理解．中文信息学报，1997，11(1)，11-19
[74] 龚千炎．汉语的时相时制时态．北京：商务印书馆，1995
[75] 胡壮麟．语篇的衔接与连贯．上海：上海外语教育出版社，1994
[76] 黄昌宁，李涓子．语料库语言学．北京：商务印书馆，2002
[77] 黄国文．语篇分析的理论与实践—广告语篇研究．上海：上海外语教育出版社，2001
[78] 黄曾阳．HNC(概念层次网络)理论．北京：清华大学出版社，1998
[79] 计算机科学技术百科全书．北京：清华大学出版社，1998
[80] 靳光瑾．现代汉语动词语义计算理论．北京：北京大学出版社，2001
[81] 乐眉云．Cohension and the Teaching of EFL Reading，语言．语篇．语境．朱永生主编，北京：清华大学出版社，1993，205-224
[82] 李涓子，黄昌宁，杨尔弘．一种自组织的汉语词义排歧方法．中文信息学报，1999，13(3)，1-8
[83] 廖秋忠．现代汉语中动词支配成分的省略．中国语文，1984(4)，241-247
[84] 廖秋忠．现代汉语篇章中指同的表达．中国语文，1986(2)，88-96
[85] 廖秋忠．篇章中的管界问题．中国语文，1987(4)，250-261
[86] 廖秋忠．篇章与语用和句法研究．廖秋忠文集．北京：北京语言学院出版社，1992，181-207
[87] 林杏光．现代汉语辞海．北京：人民中国出版社，1994
[88] 刘群，俞士汶．汉英机器翻译的难点分析．1998中文信息处理国际会议论文集，黄昌宁主编，北京：清华大学出版社，1998，507-514
[89] 刘海军，黄河燕，陈肇雄，智能机器翻译系统中的语境处理．计算机研究与发展，1998(4)，353-357
[90] 刘东立，唐泓英，王宝库，姚天顺．汉语分析的语义网络表示法．中文信息学报，1992，6(4)，1-10
[91] 陆俭明．现代汉语时间词说略．语言教学与研究，1991(1)，25-37
[92] 罗选民．论翻译的转换单位．外语教学与研究，1992(4)，34-40
[93] 罗选民．话语分析的英汉与比较研究．长沙：湖南人民出版社，2001
[94] 陆汝钤．人工智能(下)．北京：科学出版社，1996
[95] 陆汝占，高峰，陈玉泉，靳光瑾．汉语内涵逻辑及其应用．中国中文信息学会二十周年学术会议．北京：清华大学出版社，2001，89-95
[96] 鲁川．汉语的意合网络．语言文字应用，1998，23-29
[97] 马红妹，王挺，陈火旺．汉英机器翻译中语境知识的表示与应用．自然语言理解与机器翻译，黄昌宁，张普主编，北京：清华大学出版社，2001，278-284
[98] 马红妹，齐璇，王挺，陈火旺．汉英机器翻译中汉语篇章时间信息系统模型．计算机工程与科学，2002(4)
[99] 马红妹，王挺，陈火旺．汉语篇章时间短语的分析与时制验算．计算机研究与发展．2002(10)
[100] 马红妹，王挺，陈火旺．汉英机器翻译中主语省略句的处理．第一界学生计算语言学研讨会，北京大学，2002，203-208
[101] 马红妹，齐璇，王挺，陈火旺．汉语篇章中无标指同表达式的指称消解．计算机研究与发展．2002(增刊)
[102]麻志毅，林鸿飞，姚天顺．基于情境的文本中时间信息分析．东北大学学报(自然科学版)，1999，20(3)，239-242
[103]梅家驹．同义词词林．上海：上海辞书出版社，1996
[104]潘文国．汉英语对比纲要．北京：北京语言文化大学出版社，1997
[105]齐璇，陈火旺．ICENT汉英机译系统中的语义模型．计算机科学，2002，29(1)，44-46
[106]齐璇．汉语语义知识的表示及其在汉英机译中的应用．博士学位论文，国防科大研究生院，2002
[107]瞿宗德．汉语中主语隐现句及其英译．上海海运学院学报，1997，18(2)，106-114
[108]史晓东．Machine Translation-A Practitioner's Approach．博士学位论文，国防科学技术大学研究生院，1994
[109]史忠植．知识发现．北京：清华大学出版社，2002
[110]宋柔．汉语叙述文中的小句前部省略现象初析．中文信息学报，1992，6(3)，62-68
[111]王厚峰．汉语省略的判定于恢复研究．HNC与语言学研究．武汉：武汉理工大学出版社，2001，236-241
[112]王厚峰，何婷婷．汉语中人称代词的消解研究．计算机学报，2001，24(2)，136-143
[113]王建平．语境研究的历史与现状．语境研究论文集／(日)西殑光正编．北京：北京语言学院出版社，1992，6-25
[114]王挺．面向机器翻译的语料加工和知识获取的研究．博士学位论文，国防科学技术大学研究生院，1997
[115]王寅．语义理论与语言教学．上海：上海外语教育出版社，2001
[116]吴立德．大规模中文文本处理．上海：复旦大学出版社，1997
[117]吴鹤龄，崔林．ACM图灵奖(1966～1999)：计算机发展史的缩影．北京：高等教育出版社，2000
[118]吴为章，田小琳．汉语句群．北京：商务印书馆，2000
[119]徐赳赳．话语分析二十年．外语教学与研究，1995(1)，14-20
[120]薛翠芳，李晓黎，郭炳炎．汉语文摘系统中文本结构的自动分析．语言工程．陈力为，袁琦主编．北京：清华大学出版社，1997，332-337
[121]俞士汶等．现代汉语语法信息词典详解．北京：清华大学出版社，1998
[122]俞士汶．计算语言学的应用研究与基础研究．中国中文信息学会二十周年学术会议．北京：清华大学出版社，2001，54-65
[123]语言学百科词典．上海：上海辞书出版社，1993
[124]张益民，陆汝占，沈李斌．一种混合型的汉语篇章结构自动分析方法．软件学报，2000，11(11)，1527-1533
[125]赵铁军．汉英双向机器翻译中基于模式方法与混合策略的研究．博士学
位论文，哈尔滨工业大学，1998
[126]赵铁军，李生，孟遥，黄玉，杨沐昀．机器翻译系统中句法分析技术的研究实践．中国中文信息学会二十周年学术会议．北京：清华大学出版社，2001，249-257
[127]赵世开．汉英对比语法论集．上海：上海外语教育出版社，1999
[128]郑杰，茅于杭，董清富．基于语境的语义排歧方法．中文信息学报，2000(5)，1-7
[129]周会平，王挺，陈火旺．用LR算法分析汉语的语法关系．软件学报，1999(9)
[130]周会平．基于中间语言的汉英翻译系统ICENT的研究与实现，博士学位论文，国防科学技术大学研究生院，1999
[131]周强，詹卫东，任海波．构建大规模的汉语语块库．自然语言理解与机器翻译，黄昌宁，张普主编，北京：清华大学出版社，2001，102-115
[132]邹崇理．自然语言逻辑研究．北京：北京大学出版社，2000