摘要
文本蕴涵研究的主要任务是文本蕴涵识别,在自然语言处理中有很多应用。但现有文本蕴涵识别效果离大规模应用还有一定距离。一个重要原因是文本蕴涵及其识别涉及的语言理据和方法还有待进一步深挖或改进,这正是本文要做的主要工作。
研究内容方面,现有汉语文本蕴涵理据的研究主要集中在词语关系、句法转换等。本研究尝试利用语义-文本理论(Meaning-text theory)的词汇函数完善对词语关系的表达和分析,特别是将意象图式作为文本蕴涵的理据,用来表示文本蕴涵识别所需的语言知识信息。
文本蕴涵的识别方法方面,现有的句法依存分析不足以揭示文本蕴涵所需的语言信息。本研究采用概念依存分析来完善句法依存分析。但概念依存分析也无法挖掘文本蕴涵背后的所有语言理据,如元语言功能、抽象概念与具体言语表达间的对应关系。词汇函数可用来描述这些理据。
意象图式之所以能成为文本蕴涵的理据,是因为其具有理想性、规约性、可预测性。对常识加以规约化,可以提高文本蕴涵识别中语料的覆盖率。词汇函数和意象图式都有规约化常识的功能,两者在规约化常识方面具有互补性。文本蕴涵识别作为文本推理、理解的主要过程,涉及各种认知机制,如概念整合、隐喻、转喻等。针对这些问题,不是单一分析方法就能明确所有的理据,也不是单一理论就能够解释所有的现象。为此,本文采取了综合的方法和多角度的解释。比如,利用词汇函数来填补基于图式映射的概念依存分析的许多空白,除了概念整合理论外,还利用其它一些理论如默认理论、关联理论、顺应理论等来解释汉语文本蕴涵识别中涉及的有关问题和现象。
全文分九章,主要内容或观点如下：
第一章是绪论,说明文本蕴涵的概念、选题缘由、研究现状、内容、目的和意义,并介绍本研究主要理论背景、方法和资源。
第二章对文本蕴涵的类型加以划分和界定,并讨论文本语义蕴涵识别方法及其识别过程中涉及的理据。本章主要利用框架依存分析和词汇函数对语义蕴涵进行分析。分析结果显示,概念依存分析可以有效识别文本语义蕴涵;概念依存分析与词汇函数在文本蕴涵识别中具有互补性；转喻不一定都基于意象图式。
第三章研究文本语义预设的识别和涉及的理据。分析表明,意象图式在文本语义预设识别中有重要作用,概念依存分析的根本理念或操作是从概念结构到具体语句间的图式投射,而不是体现在对具体文本内部语义关系的分析。
第四章研究文本规约会话含义的识别和理据并探讨文本蕴涵识别中常识的规约化问题。分析表明：(1)文本规约会话含义最能体现各类意象图式和概念依存分析的作用,特别是框架和框架依存分析的作用；(2)以意象图式为理据的文本蕴涵识别过程中,基于意象图式的压缩有效地扩展了概念整合理论有关关键关系压缩的范围；(3)概念依存分析与概念整合间有着密切的联系；(4)抽象、元语言性概念与具体、体验性表达间的对应蕴涵关系的识别是对基于概念依存分析、词语关系、句法转换等文本蕴涵识别方法的补充。如何做好元语言性概念与体验性表达之间的衔接是完善文本蕴涵识别的重要任务之一。
第五章讨论文本结果蕴涵的识别和语言理据。分析表明,脚本在文本结果蕴涵的识别中扮演重要的角色；句法和词语关系也能体现因果关系,也能成为文本结果蕴涵的理据。
第六章基于前面的研究和对语料的梳理,初步讨论面向自然语言处理的汉语文本蕴涵识别有关资源建设问题。不同资源的构建必须考虑语言作为一个整体系统的特点。所有资源的构建,其目标是一致的：为自然语言处理领域的汉语文本蕴涵识别服务。这就要求不同资源的构建,对语料的覆盖上既要做到全面,又要避免过多交叉,达到合适的离散性。另外,不同资料间尽量避免冲突,如果无法避免冲突,也需提供解决冲突的机制。由于构建的资源是面向自然语言处理的,因而所有意象图式库必须是机器可读的,这就需要计算机专家和人才的参与。
第七章是本研究应用举例。汉语文本蕴涵识别研究的应用,既有比前面文本蕴涵识别研究简单的地方,也有复杂的地方。本章绝大部分的例子都取白汉语水平考试试题,同时体现了本研究在白然语言处理领域汉语文本蕴涵识别和汉语作为外语教学中潜在的应用价值。
第八章讨论本研究中遇到一些重要问题。包括：文本蕴涵识别的难度、概率、文本语义预设的可取消性和投射性、文本蕴涵识别涉及的隐喻和转喻等。
第九章是结论,对本研究加以总结并指出下一步可能要进行的工作。
The main task of textual entailment is recognition of textual entailment which has a lot of application in natural language processing. However, there is still a great distance between the effects of existing study of recognition of textual entailment and scale applications. One of the most important reasons is that motivations behind textual entailments need further excavation and methods used in recognition of textual entailment need further improvement, which is the main work of this paper.
The contents of existing study of textual entailment motivations mainly concentrated on word relations and syntax transformation. Word relations as textual entailment motivations are to be extended in this paper by utilizing lexical functions from Meaning-Text Theory. And especially, image schemata will be utilized as motivations behind textual entailments to express knowledge needed in recognition of textual entailments.
As far as methods of recognition of textual entailment is concerned, existing syntax dependency analysis is not enough to uncover language knowledge needed in textual entailments, which is improved by introducing conceptual dependency analysis in this paper. Nevertheless, it is found that conceptual dependency analysis cannot undertake everything in excavating linguistic motivations behind textual entailment, e.g., correspondences between meta-language functions, abstract concepts and concrete expressions cannot be excavated with conceptual dependency analysis, which can be made up by lexical functions effectively.
It is found that the reason for image schemata to become motivations behind textual entailment is that image schemata are idealized, conventionalized, and predictable. Conventionalization of common sense can improve corpus coverage in recognition of textual entailment. Both lexical functions and image schemata own the function of conventionalizing common sense and they are complementary in this function. Recognition of textual entailment, as the main procedure of textual inference and understanding, involves all kinds of cognitive mechanisms, such as conceptual integration, metonymy, and metaphor. All these problems can not be solved or explained by a single method or theory. For this reason, comprehensive methodology and multiple angles of explanation are applied in this paper. E.g., lexical functions are used to fill the gap left by conceptual dependency analysis; besides theory of conceptual integration, other theories, such as Default Theory, Relevance Theory, and Adaptation Theory are also used to explain problems and phenomena in the recognition of Chinese textual entailment.
This paper has nine chapters with the following contents or viewpoints:
Chapter1is introduction, explaining the concept of textual entailment, the reasons for choosing the topic, research status, and contents, purposes, significance of this study. Theoretical backgrounds, methods, and resources to be used in the study are also introduced.
Chapter2classifies and defines textual entailments; and discusses the recognition ways of and motivations behind textual semantic entailment. Frame dependency analysis and lexical functions are the main measures utilized in the recognition of textual semantic entailment. The results of analysis shows that frame dependency analysis is effective in recognizing textual semantic entailment; conceptual dependency analysis and lexical functions are complementary in recognition of textual entailment; and metonymy is not necessarily based on Image schemata.
Chapter3studies the recognition of textual semantic presupposition and motivations behind it. It is shown that image schemata play an important role in recognizing textual semantic presupposition, and the fundamental idea or operation of conceptual dependency analysis is schematic mapping from an image schema to a concrete sentence but not the analysis of interior semantic relations of a concrete sentence.
Chapter4discusses the recognition of and motivations behind textual conventional conversational implicature; and the problem of conventionalization of common sense in recognition of textual entailment. Analysis shows that:(1) textual conventional conversational implicature can best embody the usefulness of image schemata and conceptual dependency analysis, especially the function of frame dependency analysis;(2) during the recognition processes of those textual entailments with image schemata as their motivations, compressions based on image schemata effectively expand the domain of compression of key relations in theory of conceptual integration;(3) conceptual dependency analysis is closely related to conceptual integration;(4) the recognition of the correspondent entailment between abstract, meta-language concepts and concrete, embodied expressions are complementary with recognition of textual entailment uncovered by conceptual dependency analysis, word relations, and syntax transformation. How to establish the links between meta-language concepts and embodied expressions is one of the important tasks for improving recognition of textual entailment.
Chapter5discusses the recognition of and linguistic motivations behind textual resultative entailment. Analysis shows that scripts as motivations play an important role in the recognition of textual resultative entailment, and as syntax and special word relations can also express cause-effect relations, they can be motivations of textual resultative entailment.
Based on the above study and carding of the corpus, Chapter6tentatively discusses construction of resources for recognition of textual entailment in natural language processing. While constructing these resources, characteristics of language as a united system should be considered and all the resources share the same purpose: serve recognition of textual entailment in natural language processing. And thus it is required that while constructing these resources, it should be tried to cover all the corpus, avoiding overlapping or conflicts among different resources to ensure discreteness, and if there are conflicts that cannot be avoided, mechanisms should be offered to settle the conflicts. As these resources are natural language processing oriented, all the image schema resources must be machine readable, which means that experts in computing are needed in resource construction.
Chapter7offers examples of application of this study. Application of recognition of textual entailment has both simpler and more complex places than the study of recognition of textual entailment above. Most of the examples come from Chinese Proficiency Test, which embodies the application potential of the study above both in recognition of textual entailment in natural language processing and teaching Chinese as a second language.
Chapter8explains some problems involved in this study. There are many problems appearing during the process of this study and only some of which the author thought to have certain depth of understanding are chosen to be discussed with certain detail and these problems discussed are:the difficulty and probabilistic of recognition of textual entailment, cancellability and projectivity of textual semantic entailment, and metaphor and metonymy involved in recognition of textual entailment.
Chapter9is the conclusion, summarizing this study and pointing out the possible future work.
引文
[1]陈喜荣.会话含义与隐含[J].四川外语学院学报,2003(4)：85-88.
[2]陈意德.认知、预设及预设推理[J].中国外语,2005(5)：30-33.
[3]褚静.中英预设触发语研究综述[J].沈阳工程学院学报(社会科学版),2007(3)：410-412.
[4]戴宁淑.语义预设的界定与鉴别[J].河南师范大学学报(哲学社会科学版),2012(5)：236-239.
[5]丁建新,秦勇.英语-ing非限定小句意象图式中句法象似性的研究[J].外语教学与研究,2009(6)：425—430.
[6]范晓、陈忠.预设和蕴涵[J].信阳师范学院学报(哲学社会科学版),2002(5)：68-73.
[7]冯志伟.从格语法到框架网络[J].解放军外国语学院学报,2006,3：1-9.
[8]韩力扬,陈红.论预设的认知语境构建功能[J].河北学刊,2010(2)：242-245.
[9]黄缅.会话含义的不确定性——心智哲学新解[J].外国语文,2011(4)：56-60.
[10]黄鸣.格赖斯会话含义理论与语用推理[J].西南科技大学学报(哲学社会科学版),2011(6)：31-35.
[11]胡清芬,林崇德.反事实思维与因果推理的关系[J].湖南大学学报(社会科学版),2004(1)：95—98.
[12]姜望琪.会话含义新解[J].外语与外语教学.2012(3)：16-19,45.
[13]姜望琪.关于会话含义的再思考——兼答王晓军先生[J].外国语言文学,2010(2)：73-79.
[14]金立.会话含义的分类及其思考[J].浙江社会科学,2003(5)：130-135.
[15]李继先.形容词性短语在广义因果关系句中之特殊语用规则[J].甘肃社会科学,2009：87—89.
[16]李雯婧.预设研究综述[J].安徽文学,2008(3)：264-265.
[17]刘晶,唐德根.关联-顺应模式与跨文化交际会话含义的推断[J].长江大学学报(社会科学版),2005(2)：109-112.
[18]刘宇红.从格语法到框架语义学再到构式语法[J].解放军外国语学院学报,2011,34(1)：5-9,62.
[19]罗左毅.会话含义理论的语言学研究前景[J].四川外语学院学报,2003(1)：55-58.
[20]马荣.概念整合理论的基本原理探讨[J].广西社会科学,2011,(1)：123-125.
[21]苗原,等.基于模糊认知图的因果推理[J].模式识别与人工智能,1999(2)：143 -151.
[22]梅明玉.语义蕴涵关系层级类型及推理机制分析[J].山东外语教学,2010(3)：14-18.
[23]彭湃.现代汉语因果关系连接成分研究综述[J].汉语学习,2004(2)：44-48.
[24]邱广君,等.汉语信息处理中的语义关系类型分析[J].东北大学学报(自然科学版),1998(2)：48-51.
[25]束定芳.论隐喻的本质及语义特征[J].外国语,1998(6)：10—18.
[26]束定芳.认知语义学的基本原理、研究目标与方法[J]。山东外语教学；2005,(5)：3-11.
[27]孙玉.会话含义的可取消性再探[J].外国语,2010(5)：52-59.
[28]苏兰姣.预设研究综述[J].重庆工学院学报(社会科学),2008(9)：38-41.
[29]孙永强.浅谈英语中表达因果关系的动词的用法[J].黑龙江矿业学院学报,1994(1)：59-64.
[30]陶明忠,马玉蕾.框架语义学—格语法的第三阶段[J].当代语言学,2008(1)：35-42.
[31]王文博.预设的认知研究[J].外语教学与研究,2003(1)：34-39。
[32]王相锋.会话含义与语言结构[J].外语学刊,2002(2)：22-27.
[33]王晓飞.论取消会话含义的潜在可能与实际发生——兼驳“含义不可取消论”[J].外语与外语教学,2012(3)：37-40.
[34]王寅.认知语义学[J].四川外语学院学报,2002(2)：58-62.
[35]王跃平.试析语义蕴涵的基本特征[J].徐州师范大学学报(哲学社会科学版),2005(9)：42-46.
[36]王跃平.语义预设与规约隐涵[J].扬州大学学报(人文社会科学版),2007(1)：33-37.
[37]魏在江.认知参照点与语用预设[J].外语学刊,2008(3)：93-97。
[38]宣恒大.论汉语的具象性[J].合肥师范学院学报,2008(04)：111—113.
[39]萧国政,等.从概念基元空间到语义基元空间的映射[J].华东师范大学学报(哲学和社会科学),2011a(1)：139-143.
[40]萧国政,等,Ontology的类型及汉语词网的Ontology结构[J].长江学术,2011b(2)：111-117.
[41]谢广平,陈德喜.浅论蕴涵[J].安徽理工大学学报(社会科学版),2006(6)：52-55.
[42]徐盛桓.论蕴涵[J].山东外语教学,1992(1-2)：90-94.
[43]杨年保.语义预设与语用预设研究[J].云梦学刊,2005(3)：119-121.
[44]袁毓林.论元角色的层级关系和语义特征[J].世界汉语教学,2002(3)：10-22.
[45]袁毓林,王明华.文本蕴涵的推理模型与识别模型[J].中文信息学报,2010,24(2)：3-13.
[46]曾欣悦.认知语义学的六个基本特征[J].外语研究,2008,(5)：20-23.
[47]张济卿.对汉语时间系统三元结构的一点看法[J].汉语学习,1998(5)：20—23.
[48]张利明.关于预设和蕴涵[J].安徽文学,2008(3)：273-274.
[49]张鹏,等.基于框架网框架关系的文本蕴涵识别[J].中文信息学报,2012(2)46-50.
[50]张绍杰,张延飞.默认理论与关联理论——解释“一般会话含义”的两种对立方法[J].当代外语研究,2012(7)：19—23.
[51]郑亚南,黄齐东.预设的认知语境研究[J]。南京社会科学,2007(10)：121-127.
[52]郅丽梅.语用预设与交际语境顺应[J].山西财经大学学报,2011(5)：88-107.
[53]朱德熙.自指和转指——汉语名词化标记“的、者、所、之”的语法功能和语义功能[J].方言,1983(1)：16—31.
[54]Abrusan M. Predicting the presuppositions of soft triggers[J]. Linguistics and philosophy,2012:1-45.
[55]Abusch D. Presupposition triggering from alternatives[J]. Journal of Semantics,2010, 27(1):37-80.
[56]Blome-Tillmann M. Conversational implicature and the cancellability test[J]. Analysis, 2008,68(2):156-160.
[57]Bouton, L. F. Conversational Implicature in a 2nd-Language Learning Slowly when not Deliberately Taught[J]. Journal ofPragmatics,1994(2):157-167.
[58]Burchardt A, Pennacchiotti M, Thater S, et al. Assessing the impact of frame semantics on textual entailment[J]. Natural Language Engineering,2009,15(4):527-550.
[59]Chemla E. Presuppositions of quantified sentences:experimental data[J]. Natural Language Semantics,2009,17(4):299-340.
[60]Chemla E, Schlenker P. Incremental vs. symmetric accounts of presupposition projection:An experimental approach[J]. Natural language semantics,2012:1-50.
[61]Fauconnier G, Turner M. Conceptual integration networks[J]. Cognitive science,1998, 22(2):133-187.
[62]Fauconnier G, Turner M. Metonymy and conceptual integration[J]. Metonymy in language and thought,1999:77-90.
[63]Fernandez O, Terol R M, Munoz R, et al. Deep vs. shallow semantic analysis applied to textual entailment recognition[J]. Advances in Natural Language Processing. Springer Berlin Heidelberg,2006:225-236.
[64]Fillmore C. Frame semantics[J]. Linguistics in the morning calm,1982:111-137.
[65]Gauker C. Situated inference versus conversational implicature[J]. Nous,2001,35(2): 163-189.
[66]Gordon P C, Hendrick R. Intuitive knowledge of linguistic co-reference[J]. Cognition, 1997,62(3):325-370.
[67]Ippolito M. Semantic composition and presupposition projection in subjunctive conditionals[J]. Linguistics and Philosophy,2006,29(6):631-672.
[68]Ippolito M. A Note on Embedded Implicatures and Counterfactual Presuppositions[J]. Journal of Semantics,2011,28(2):267-278.
[69]Jackson S. Conversational implicature in children's comprehension of reference[J]. Communications Monographs,1981,48(3):237-249.
[70]Jaszczolt K M. Against ambiguity and underspecification:Evidence from presupposition as anaphora[J]. Journal of pragmatics,2002,34(7):829-849.
[71]Kahane S. The meaning-text theory[J]. Dependency and Valency, Handbooks of Linguistics and Communication Sciences 25:1,2003,2.
[72]Kallulli D. Belief will create fact:On the relation between givenness and presupposition, and other remarks[J]. Theoretical Linguistics,2010,36(2-3):199-208.
[73]Karttunen, L. Implicative Verbs[J] 1971a, Language 47(2):340-358.
[74]Karttunen, L. Some Observations on Factivity[J]. Papers in Linguistics 1971b, (4):I, 55-69.
[75]Karttunen, L. Counterfactual conditionals[J]. Linguistic Inquiry,1971c,2(4):566-569.
[76]Karttunen L. Presuppositions of compound sentences[J]. Linguistic inquiry,1973,4(2): 169-193.
[77]Karttunen L. Presuppositions of compound sentences[J]. Linguistic inquiry,1973,4(2): 169-193.
[78]Keenan E L. Two kinds of presupposition in natural language[J]. Studies in linguistic semantics,1971:45-54.
[79]Kripke S A. Presupposition and anaphora:Remarks on the formulation of the projection problem[J]. Linguistic Inquiry,2009,40(3):367-386.
[80]Lasnik H. Remarks on coreference[J]. Linguistic analysis,1976,2(1):1-22.
[81]Levinson S C. Three levels of meaning[J]. Grammar and meaning,1995:90-115.
[82]McDonald S. Differential pragmatic language loss after closed head injury:Ability to comprehend conversational implicature[J]. Applied Psycholinguistics,1992,13: 295-295.
[83]Mel'cuk I. and A. Polguere. A Formal Lexicon[J]. Computational Linguistics,1988,vol 13,nos.3-4.
[84]Mel'cuk I. Lexical functions:a tool for the description of lexical relations in a lexicon[J]. Lexical functions in lexicography and natural language processing,1996,31:37-102.
[85]Mel'cuk I. Actants in semantics and syntax Ⅰ:Actants in semantics[J]. Linguistics,2004: 1-66.
[86]Mori Y, Yoshimoto K. If a Quantifier is not floated, but moored or even incorporated: Complexity of Presuppositions in Local Domain[J]. Language, Information, and Computation, Proceedings,2002:330-347.
[87]Murray W.R. Conceptual metaphor and scripts in Recognizing Textual Entailment[J]. Natural Language Processing and Cognitive Science,2008:127-136.
[88]Nanay B. Imaginative resistance and conversational implicature[J]. The Philosophical Quarterly,2009,60(240):586-600.
[89]Nivre J. Dependency grammar and dependency parsing[J]. MSI report,2005, 5133(1959):1-32.
[90]Pakray P. Answer validation through textual entailment[J]. Natural Language Processing and Information Systems,2011:324-329.
[91]Percival W K. Reflections on the history of dependency notions in linguistics[J]. Historiographia linguistica,1990,17(1-2):1-2.
[92]Pustejovsky J. Type Theory and Lexical Decomposition[J]. Journal of Cognitive Science, 2006,6:39-76.
[93]Ruppenhofer J, Ellsworth M, Petruck M R L, et al. FrameNet Ⅱ:Extended theory and practice[J].2010:5-113.
[94]Schmid H J.'Presupposition can be a bluff':How abstract nouns can be used as presupposition triggers[J]. Journal of pragmatics,2001,33(10):1529-1552.
[95]Schlenker P. Presupposition projection:Explanatory strategies[J]. Theoretical Linguistics,2008a,34(3):287-316.
[96]Schlenker P. Be Articulate:A pragmatic theory of presupposition projection[J]. Theoretical Linguistics,2008b,34(3):157-212.
[97]Stalnaker R. Pragmatic presuppositions[J]. Semantics and philosophy,1974:197-213.
[98]Stalnaker R. Common ground[J]. Linguistics and Philosophy,2002,25(5):701-721.
[99]Verschueren J. Pragmatics as a theory of linguistic adaptation[J]. International Pragmatics Association,1987:44-65.
[100]Wang, Minhua. Conversational Implicature in the Movie Gone with the Wind[J]. International Conference on Education Science and Management Engineering (ESME), 2011, Beijing, PEOPLES R CHINA.
[101]Wilson D, Sperber D. Relevance theory[J]. Handbook of pragmatics,2002.
[102]Zanzotto F, Pennacchiotti M, Moschitti A. A machine learning approach to textual entailment recognition[J]. Natural Language Engineering,2009,15(04):551-582.
[103]Zeevat H. Particles:Presupposition triggers, context markers or speech act markers[J]. Optimality Theory and Pragmatics,2003:91-111.
[104]陈田顺.HSK中国汉语水平考试模拟试题集(初中等)[M].北京：北京语言文化大学出版社,2000.
[105]李增吉,等.新编汉语水平考试(HSK)题[M].天津：南开大学出版社,2004.
[106]刘海涛.依存语法的理论与实践[M].北京：科学出版社,2009：xvi-xvii.
[107]刘宇红.认知语言学：理论与应用[M].中国社会科学从出版社,2006：1-28.
[108]史忠植.认知科学[M].合肥：中国科学技术大学出版社,2006：215-320.
[109]张辉,卢卫中。认知转喻[M].上海：上海外语教育出版社,2010：25-38.
[110]王寅.语义理论与语言教学[M].上海外语教育出版社,2001：192.
[111]王寅.认知语言学探索[M].重庆：重庆出版社,2005：140-141,192.
[112]王寅.认知语法概论[M].上海：上海外语教育出版社,2006：28-29.
[113]Fauconnier G, Turner M. The way we think:conceptual blending and the mind's hidden complexities[M].2002:47-396.
[114]Geeraerts D. Theories of Lexical Semantics[M]. New York:Oxford University Press, 2010:165-178,182,227-228.
[115]Halliday M. A. K.& Matthiessen, Christian M. I. M. An Introduction to Functional Grammar (3rd Edition)[M]. London:Arnold,2004.
[116]Harmeling S. Inferring textual entailment with a probabilistically sound calculus[J]. Natural Language Engineering,2009,15(04):459-477.
[117]Herrera J, Penas A, Verdejo F. Techniques for recognizing textual entailment and semantic equivalence[M]. Current Topics in Artificial Intelligence. Springer Berlin Heidelberg,2006:419-428.
[118]Kozareva Z, Montoyo A. An approach for textual entailment recognition based on stacking and voting[M]. MICAI 2006:Advances in Artificial Intelligence. Springer Berlin Heidelberg,2006:889-899.
[119]Krahmer E. Presupposition and anaphora[M]. University of Chicago Press,1998.
[120]Langacker R W. Cognitive grammar:A basic introduction[M]. Oxford University Press, 2008:3-85.
[121]Lakoff G. Women, Fire, and Dangerous Things[J]. U-niversity of Chicago Press, Chicago,1987:68-71,74,106,159-376,489.
[122]Lakoff G, Johnson M. Metaphors we live by[M]. London:Chicago,2003:246,253.
[123]Levinson S C. Presumptive meanings:The theory of generalized conversational implicature[M]. MIT press,2000.
[124]Negri M, Kouylekov M, Magnini B, et al. Towards Extensible Textual Entailment Engines:the EDITS Package[M]. AI* IA 2009:Emergent Perspectives in Artificial Intelligence. Springer Berlin Heidelberg,2009:314-323.
[125]Ofoghi B, Yearwood J. Learning Parse-Free Event-Based Features for Textual Entailment Recognition[M]. AI 2010:Advances in Artificial Intelligence. Springer Berlin Heidelberg,2011:184-193.
[126]Pazienza M T, Pennacchiotti M, Zanzotto F M. Learning textual entailment on a distance feature space[M]//Machine Learning Challenges. Evaluating Predictive Uncertainty, Visual Object Classification, and Recognising Tectual Entailment. Springer Berlin Heidelberg,2006:240-260.
[127]Pustejovsky J. The generative lexicon[M]. MIT Press,1996:85-140.
[128]Schank R C, Abelson R P. Scripts, plans, and knowledge[M]. Yale University,1975:24, 26.
[129]Sperber D, Wilson D,何自然，等导读.Relevance:Communication and cognition[M]. Cambridge, MA:Harvard University Press,1986:preface.
[130]Ungerer, F.& Schmid,H.J. An Introduction to Cognitive Linguistics[M]. Beijing: Foreign Language Teaching and Research Press,2001:27,114-155.
[131]Vershcueren, J. Understanding Pragmatics[M]. Shanghai:Shanghai Foreign Language Teaching and Research Press,2000:F1-F14.
[132]冯志伟.关于术语ontology的中文译名-“本体论”与“知识本体”[A].第六届汉语词汇语义学研讨会论文集[M],2005：1-17.
[133]伍丽梅,莫雷.说明文阅读中局部连贯因果推理的产生[A].第十二届全国心理学学术大会论文[M],2010：200—215.
[134]Delmonte R, Bristot A, Boniforti M A P, et al. Entailment and anaphora resolution in Recognition Textual Entailment[A]. Proceedings of the ACL-PASCAL Workshop on Textual Entailment and Paraphrasing[C]. Association for Computational Linguistics, 2007:48-53.
[135]Feng J, Zhou Y, Martin T. Combining Lexical Resources with Fuzzy Set Theory for Recognizing Textual Entailment[A]. Business and Information Management[C],2008, ISBIM'08. International Seminar on IEEE,2008,2:54-57.
[136]Mel'cuk I. Lexical Functions in Lexicographic Description[A], Procedings. of the 8th Annual Meeting of Berkeley Linguistic Society[C],1982.
[137]Morton T S. Coreference for Natural Language Peocessing applications[A]. Proceedings of the 38th Annual Meeting on Association for Computational Linguistics[C]. Association for Computational Linguistics,2000:173-180.
[138]Ou S, Mekhaldi D, Orasan C. An ontology-based question answering method with the use of textual entailment[A]. Natural Language Processing and Knowledge Engineering[C],2009. NLP-KE 2009. International Conference on IEEE,2009:1-8.
[139]Pakray P, Bandyopadhyay S, Gelbukh A. Dependency Parser Based Textual Entailment System[A]. Artificial Intelligence and Computational Intelligence (AICI) [C],2010 International Conference on. IEEE,2010a,1:393-397.
[140]Pakray P, Bandyopadhyay S, Gelbukh A. Textual Entailment and anaphora resolution[A]. Advanced Computer Theory and Engineering (ICACTE) [C],2010 3rd International Conference on. IEEE,2010b,6:V6-334-V6-336.
[141]Su R, Zheng Y. Chinese Textual Entailment recognition model based on lexical and semantic matching[A]. Natural Language Processing and Knowledge Engineering (NLP-KE) [C],2011 7th International Conference on. IEEE,2011:92-99.
[142]冯志伟.词汇语义学与知识本体[A].应用语言学前沿讲座[M].北京：中国传媒大学出版社，2005：1-25。
[143]宋作艳.生成词库理论的最新发展[A].见《语言学论丛》第44辑[M].北京：商务印书馆,2011,202—221.
[144]Melcuk, I. Meaning-Text Models[A]. In Annual Review of Anthropology[M],1981, vol.10:27-62.
[145]陈波.特征结构及其汉语语义资源建设[D].武汉大学,2011.
[146]冯文贺.汉语连词及其相关结构的依存分析[D].武汉大学,2011.
[147]韩亦佳.蕴涵与因果推理的关系[D].河南大学,2008.
[148]刘涛.含因果关系单句探讨[D].东北师范大学,2002.
[149]刘丽梅.工作记忆对中国英语学习者即时因果推理的影响[D].中国海洋大学,2009.
[150]齐志.预设的认知研究[D].西南师范大学外国语学院,2002.
[151]汪梦翔.因果关系关联词套用现象分析[D].华中师范大学,2009.
[152]杨静.预设在汉语研究中的应用及其特征提取[D].华中师范大学,2005.
[153]杨唐风.会话含义的认知分析[D].上海外国语大学,2004.
[154]郑特军.儿童早期因果推理的实验研究[D].西南师范大学,2001.
[155]Fauconnier G, Turner M. Conceptual projection and middle spaces[R]. Technical Report 9401, University of California at San Diego,1994. Dept. of Cognitive Science, 1994:19-169.
[156]Kruijff G J M. Formal and computational aspects of dependency grammar:History and development of dependency grammar [R]. Technical report,2002:18-58.
[157]北京大学语料库.http://ccl.pku.edu.cn:8080/ccl corpus/index.jsp?dir=xiandai.
[158]语料库在线http://www.cncorpus.org/login.aspx.
[159]FrameNet. https://framenet.icsi.berkeley.edu/fndrupal/.
[160]HowNet. http://www.keenage.com/.
[161]VerbNet:http://verbs.colorado.edu/-mpalmer/projects/verbnet.html.
