面向文景转换的中文浅层语义分析方法研究
|
摘要
本文针对中文浅层语义分析中的关键问题展开了全面深入的研究。浅层语义分析是自然语言处理领域里的研究要点,基于语言学特征和统计机器学习的方法是目前浅层语义分析的主流方法,该方法中最关键的因素是特征的选择和机器学习方法的优化。另外,本文中的浅层语义分析主要面向文景转换这项应用任务,文景转换是指把自然语言文本通过计算机自动转换成为相应的场景或动画,是一门具有重要理论和实际意义的新兴研究方向。本文首先对文景转换中必要的共指消解模块进行了研究;然后从特征选择角度对浅层语义分析方法进行了探索,发掘出在浅层语义分析中具有较强区分能力的句法特征;接着提出一种组合分类模型的方法对浅层语义分析进行完善;最后提出一种基于计算认知模型的方法,从更深层面对中文浅层语义分析进行了探索。具体地说,本文主要包括以下研究内容:
(1)首先提出一种基于自适应谐振理论(ART)网络的无指导中文名词短语共指消解方法。该方法充分利用了名词短语自身特征,通过调整ART网络模型中的参数动态地控制聚类数量,有效解决了目前聚类共指消解中输出类别数目难以确定这一难题。另外聚类算法中还采用了一种基于信息增益率的特征选择方法,减少了区分度较弱特征给聚类所带来的干扰。该方法在保证了共指消解准确率的前提下,具有较好的可移植性和鲁棒性,突破了目前文景转换中的浅层语义分析在预处理阶段的主要障碍。
(2)本文从语言学特征层面深入地研究了中文浅层语义分析,提出一种基于多重句法特征的中文浅层语义分析方法。现有研究表明,对特征集合进行改进是目前提高浅层语义分析性能最有效的方法。本文提出将短语结构句法和依存句法两种类型的句法特征进行融合,为浅层语义分析提供了更加丰富和互补的句法信息。然后在这两个句法特征集合基础上,提出一种基于统计的组合特征选择方法,根据各个特征在语料库中的分布状况,快速有效地筛选出适于各分类阶段的组合特征。最后利用短语结构句法特征、依存句法特征以及在前两者基础上构造的组合特征进行语义分析相关的分类。实验表明,本文提出的多重句法特征集合能够有效地提高中文浅层语义分析的性能,在正确句法分析以及自动句法分析条件下均取得了较好的效果。
(3)提出了一种基于组合分类模型的中文浅层语义分析方法,从优化机器学习方法的层面进一步对浅层语义分析进行完善。本文在前面提出的多重句法特征集合基础上,采用五种机器学习方法:K近邻、决策树、感知器、最大熵以及支持向量机,在训练语料上构造了五个语义角色分类模型,作为组合模型中的基本单元。接着通过一种输入相关的选通系统将五个基本分类模型有机地整合到一起,通过调整选通系统中的参数协调各个基本分类模型,控制组合模型的输出结果。最后采用EM算法在训练语料上对选通系统中的参数进行学习,在通用语料库上进行了相关的训练和测试,结果表明该方法能够显著地提高中文语义角色分析的效果。
(4)最后,本文提出了探索性的基于计算认知模型的中文浅层语义分析方法,以认知理论为基本依据,通过模拟人类的语言理解过程,从本质上来研究中文浅层语义分析。首先设计了一种面向计算认知模型和文景转换的命题语义表示形式,这种命题形式能够简单高效地表达自然语言中蕴涵的语义信息。本文将该命题形式作为认知模型中的基本单元,然后在认知模型网络上模拟人脑中神经元的扩散激活机制,使符合上下文约束的命题节点不断被加强,不符合上下文约束的节点逐渐被削弱,根据当网络达到稳定状态时的最终激活命题节点,即可还原出谓词相关的语义分析结果。
In this paper, we conduct comprehensive and deep academic research on the key issues of Chinese shallow semantic parsing (SSP). SSP is an essential research in the area of Natural Language Processing (NLP). Currently, the method based on linguistic features and statistical machine learning is the most prevalent method for SSP. The method involves two key factors: selection of linguistic features and optimization of machine learning method. Additionally, the SSP rearch in this paper is oriented to the Text-to-Scene conversion, which is to automatically convert the natural language text to the corresponding scene or animation by computer. It is a novel research area that has important theoretical and practical significance. Firstly, we study coreference resolution which is a necessary pre-processing module for the Text-to-Scene conversion. Secondly, we explore the issue of SSP from the perspective of linguistic feature selection and discover many discriminative syntactic features. Then, we propose a combined machine learning method to further improve the SSP. Finally, we study the issue from a deeper level and proposes a computational cognitive model-based approach to SSP. Specifically, this paper includes following contents:
(1) Firstly, we propose an Adaptive Resonance Theory (ART) network-based unsupervised noun phrase coreference resolution method for Chinese. The method makes fully use of the features of noun phrase. It can dynamically control the amount of cluster by adjusting the parameters of the ART network. Thus it provides an effective solution to the critical problem of cluster-based coreference resolution that the output cluster number, namely the number of the coreference set is difficult to determine or evaluate. Additionally, in the clustering algorithm, we use an information gain ratio-based feature selection method to reduce the interference caused by some weak clustering features. This method achieves a relative high accuracy of coreference resolution and it has good portability and robustness. It addresses the major obstacle of the pre-processing phase in the Chinese SSP in the Text-to-Scene conversion.
(2) Then, we intensively study the linguistic features for Chinese SSP and then propose a multiple syntactic features-based method. Current researches show that improving the linguistic feature set is the most effective method to enhance the performance of SSP at present. The proposed method integrates constituent-based and dependency-based syntactic features into a basic feature set, and thus provides more extensive and complementary syntactic information to SSP. Further we propose a statistical combined feature selection method on the basis of the basic feature set. The statistical method can efficiently select discriminative combined features according to the distribution of each combined features in the corpus. Finally, we use the constituent-based syntactic features, the dependency-based syntactic features and the selected combined feature for classifications in SSP. Experiments show that the proposed method achieves better results on both gold-standard and automatic syntactic parsing.
(3) Further, we propose a combined machine learning method which is to improve SSP from the perspective of optimizing machine learning method. The proposed method is based on the above mentioned multiple syntactic features. It adopts five basic machine learning methods: K-Nearest Neighbor, Decision Tree, Perceptron, Maximum Entropy, and Support Vector Machine. We construct the five classification model using the five machine learning methods on the training corpus as the basic unit of the combined model. Then we use an input-dependent gating system to integrate the five basic classification models, and control the output of the combined model by adjusting the parameters of the gating system. Finally, we use Expectation Maximization algorithm to learn the parameters of the gating system using training data, and experimental results show that the method can significantly improve the effect of Chinese SSP.
(4) At last, this paper proposes an exploratory computational cognitive model-based Chinese SSP method. On basis of cognitive theory, the method simulates the language understanding process of human and then explores semantic analysis and calculations from fundamental properties. First we define propositional semantic representation oriented to the cognitive model and the Text-to-Scene conversion. The propositions can simply and efficiently express the semantics of natural language. We take the propostions as the neurons of the cognitive model. Then the contextually appropriate propositions will be gradually strengthened and inappropriate ones will be inhibited through iteratively spreading activations until the network stabilizes. Finally, the result of SSP can be achieved according to the activated propostions in the cognitive model.
(1)首先提出一种基于自适应谐振理论(ART)网络的无指导中文名词短语共指消解方法。该方法充分利用了名词短语自身特征,通过调整ART网络模型中的参数动态地控制聚类数量,有效解决了目前聚类共指消解中输出类别数目难以确定这一难题。另外聚类算法中还采用了一种基于信息增益率的特征选择方法,减少了区分度较弱特征给聚类所带来的干扰。该方法在保证了共指消解准确率的前提下,具有较好的可移植性和鲁棒性,突破了目前文景转换中的浅层语义分析在预处理阶段的主要障碍。
(2)本文从语言学特征层面深入地研究了中文浅层语义分析,提出一种基于多重句法特征的中文浅层语义分析方法。现有研究表明,对特征集合进行改进是目前提高浅层语义分析性能最有效的方法。本文提出将短语结构句法和依存句法两种类型的句法特征进行融合,为浅层语义分析提供了更加丰富和互补的句法信息。然后在这两个句法特征集合基础上,提出一种基于统计的组合特征选择方法,根据各个特征在语料库中的分布状况,快速有效地筛选出适于各分类阶段的组合特征。最后利用短语结构句法特征、依存句法特征以及在前两者基础上构造的组合特征进行语义分析相关的分类。实验表明,本文提出的多重句法特征集合能够有效地提高中文浅层语义分析的性能,在正确句法分析以及自动句法分析条件下均取得了较好的效果。
(3)提出了一种基于组合分类模型的中文浅层语义分析方法,从优化机器学习方法的层面进一步对浅层语义分析进行完善。本文在前面提出的多重句法特征集合基础上,采用五种机器学习方法:K近邻、决策树、感知器、最大熵以及支持向量机,在训练语料上构造了五个语义角色分类模型,作为组合模型中的基本单元。接着通过一种输入相关的选通系统将五个基本分类模型有机地整合到一起,通过调整选通系统中的参数协调各个基本分类模型,控制组合模型的输出结果。最后采用EM算法在训练语料上对选通系统中的参数进行学习,在通用语料库上进行了相关的训练和测试,结果表明该方法能够显著地提高中文语义角色分析的效果。
(4)最后,本文提出了探索性的基于计算认知模型的中文浅层语义分析方法,以认知理论为基本依据,通过模拟人类的语言理解过程,从本质上来研究中文浅层语义分析。首先设计了一种面向计算认知模型和文景转换的命题语义表示形式,这种命题形式能够简单高效地表达自然语言中蕴涵的语义信息。本文将该命题形式作为认知模型中的基本单元,然后在认知模型网络上模拟人脑中神经元的扩散激活机制,使符合上下文约束的命题节点不断被加强,不符合上下文约束的节点逐渐被削弱,根据当网络达到稳定状态时的最终激活命题节点,即可还原出谓词相关的语义分析结果。
In this paper, we conduct comprehensive and deep academic research on the key issues of Chinese shallow semantic parsing (SSP). SSP is an essential research in the area of Natural Language Processing (NLP). Currently, the method based on linguistic features and statistical machine learning is the most prevalent method for SSP. The method involves two key factors: selection of linguistic features and optimization of machine learning method. Additionally, the SSP rearch in this paper is oriented to the Text-to-Scene conversion, which is to automatically convert the natural language text to the corresponding scene or animation by computer. It is a novel research area that has important theoretical and practical significance. Firstly, we study coreference resolution which is a necessary pre-processing module for the Text-to-Scene conversion. Secondly, we explore the issue of SSP from the perspective of linguistic feature selection and discover many discriminative syntactic features. Then, we propose a combined machine learning method to further improve the SSP. Finally, we study the issue from a deeper level and proposes a computational cognitive model-based approach to SSP. Specifically, this paper includes following contents:
(1) Firstly, we propose an Adaptive Resonance Theory (ART) network-based unsupervised noun phrase coreference resolution method for Chinese. The method makes fully use of the features of noun phrase. It can dynamically control the amount of cluster by adjusting the parameters of the ART network. Thus it provides an effective solution to the critical problem of cluster-based coreference resolution that the output cluster number, namely the number of the coreference set is difficult to determine or evaluate. Additionally, in the clustering algorithm, we use an information gain ratio-based feature selection method to reduce the interference caused by some weak clustering features. This method achieves a relative high accuracy of coreference resolution and it has good portability and robustness. It addresses the major obstacle of the pre-processing phase in the Chinese SSP in the Text-to-Scene conversion.
(2) Then, we intensively study the linguistic features for Chinese SSP and then propose a multiple syntactic features-based method. Current researches show that improving the linguistic feature set is the most effective method to enhance the performance of SSP at present. The proposed method integrates constituent-based and dependency-based syntactic features into a basic feature set, and thus provides more extensive and complementary syntactic information to SSP. Further we propose a statistical combined feature selection method on the basis of the basic feature set. The statistical method can efficiently select discriminative combined features according to the distribution of each combined features in the corpus. Finally, we use the constituent-based syntactic features, the dependency-based syntactic features and the selected combined feature for classifications in SSP. Experiments show that the proposed method achieves better results on both gold-standard and automatic syntactic parsing.
(3) Further, we propose a combined machine learning method which is to improve SSP from the perspective of optimizing machine learning method. The proposed method is based on the above mentioned multiple syntactic features. It adopts five basic machine learning methods: K-Nearest Neighbor, Decision Tree, Perceptron, Maximum Entropy, and Support Vector Machine. We construct the five classification model using the five machine learning methods on the training corpus as the basic unit of the combined model. Then we use an input-dependent gating system to integrate the five basic classification models, and control the output of the combined model by adjusting the parameters of the gating system. Finally, we use Expectation Maximization algorithm to learn the parameters of the gating system using training data, and experimental results show that the method can significantly improve the effect of Chinese SSP.
(4) At last, this paper proposes an exploratory computational cognitive model-based Chinese SSP method. On basis of cognitive theory, the method simulates the language understanding process of human and then explores semantic analysis and calculations from fundamental properties. First we define propositional semantic representation oriented to the cognitive model and the Text-to-Scene conversion. The propositions can simply and efficiently express the semantics of natural language. We take the propostions as the neurons of the cognitive model. Then the contextually appropriate propositions will be gradually strengthened and inappropriate ones will be inhibited through iteratively spreading activations until the network stabilizes. Finally, the result of SSP can be achieved according to the activated propostions in the cognitive model.
引文
[1] Christensen J, Mausam, Soderland S, et al. Semantic Role Labeling for Open Information Extraction[C]. Proceedings of the Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics(HLT-NAACL) 2010 First International Workshop on Formalisms and Methodology for Learning by Reading, 2010:52-60
[2] Shen D, Lapata M. Using Semantic Roles to Improve Question Answering[C]. Proceedings of the Joint Conference on Empirical Methods in Natural Language Processing (EMNLP) and Computational Natural Language Learning (CoNLL), 2007:12-21
[3] Bilotti M W, Ogilvie P, Callan J, et al. Structured Retrieval for Question Answering[C]. In Proceedings of the 30th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, New York, USA, 2007:351-358
[4] Fillmore C J, Baker C F. Frame Semantics for Text Understanding[C]. Proceedings of the North American Chapter of the Association for Computational Linguistics (NACCL) 2001 Workshop on WordNet and Other Lexical Resources, Pittsburgh, 2001
[5] Liu D, Gildea. Semantic Role Features for Machine Translation[C]. Proceedings of the 23rd International Conference on Computational Linguistics (COLING), 2010:716-724
[6] Adorni G, Manzo M D, Giunchiglia F. Natural Language Driven Image Generation[C]. Proceedings of the International Conference on Computational Linguistics(COLING). Stanford, California, 1984:495-500
[7] Coyne B, Sproat R. WordsEye: An Automatic Text-to-Scene Conversion System[C]. Proceedings of the Annual Conference on Computer Graphics, Los Angeles, USA, 2001:487-496
[8] Gruber J S. Studies in Lexical Relations[D]. Ph.D. Dissertation, Massachusetts Institute of Technology (MIT), 1965
[9] Fillmore C J. The Case for Case. In Bach and Harms (eds.): Universals in Linguistic Theory[M]. New York:Holt, Rinehart and Winston, 1968:1-88
[10] Chomsky N. Lectures on Government and Binding[M]. Dordrecht:Foris, 1981
[11] Gildea D, Palmer M. The Necessity of Syntactic Parsing for Predicate Argument Recognition[C]. Proceedings of the Association for Computational Linguistics(ACL), 2002:239-246
[12] Punyakanok V, Roth S, Yih W. The Necessity of Syntactic Parsing for Semantic Role Labeling[C]. Proceedings of International Joint Conferences on Artificial Intelligence (IJCAI). 2005: 1117-1123
[13] Baker C F, Fillmore C J, Lowe J B. The Berkeley FrameNet Project[J]. Proceedings of COLING-ACL’98 Joint Conference, 1998:86-90
[14] Kipper K, Korhonen A, Ryant N, et al. A Large-scale Classification of English Verbs[J]. Language Resources and Evaluation, 2008, (42):21-40
[15] Palmer M, Gildea D, Kingsbury P. The Proposition Bank: An Annotated Corpus of Semantic Roles[J]. Computational Linguistics, 2005, 31(1):71-106
[16] Meyers A, Reeves R, Macleod C, et al. Annotating Noun Argument Structure for NomBank[C]. Proceedings of the International Conference on Language Resources and Evaluation(LREC), 2004:803-806
[17]刘开瑛,由丽萍.汉语框架语义知识库构建工程[C].中文信息处理前沿进展——中国中文信息学会成立二十五周年学术会议论文集, 2006, (11):64-71
[18]周强.汉语句法语义链接知识库开发[C].第八届汉语词汇语义学研讨会. 2007
[19] Xue N, Palmer M. Adding Semantic Roles to the Chinese Treebank[J]. Natural Language Engineering, 2009, 15(1):143-172
[20] Xue N, Palmer M. Annotating the Propositions in the Penn Chinese Treebank[C]. Proceedings of the Second SIGHAN Workshop on Chinese Language Processing, 2003:47-54
[21] Xue N, Palmer M. Calibrating Features for Semantic Role Labeling[C]. Proceedings of the Conference on Empirical Methods in Natural Language Processing(EMNLP), 2004:88-94
[22] Toutanova K. Haghighi A, Manning C M. A Global Joint Model for Semantic Role Labeling[J]. Computational Linguistics, 2008, 34(2):161-191
[23] Mitchell T M. Machine Learning[M]. New York: McGraw-Hill, 1997
[24]李军辉.中文句法语义分析及其联合学习机制研究[D].苏州:苏州大学, 2010, 27
[25] Gildea D, Jurafsky D. Automatic Labeling of Semantic Roles[J]. Computational Linguistics, 2002, 28(3):245-288
[26] Chen J, Rambow O. Use of Deep Linguistic Features for the Recognition and Labeling of Semantic Arguments[C]. Proceedings of the Conference on Empirical Methods in Natural Language Processing(EMNLP), 2004, 41-48
[27] Surdeanu M, Harabagiu S, Williams J, et al. Using Predicate-argument Structures for Information Extraction[C]. In Proceedings of the Annual Meeting of the Association for Computational Linguistics(ACL), 2003:8-15
[28] Pradhan S, Hacioglu K, Krugler V, et al. Support vector learning for semantic argument classification[J]. Machine Learning Journal, 2005, 60(3):11-39
[29] Xue N. Labeling Chinese Predicates with Semantic Roles[J]. Computational Linguistics, 2008, 34(2):225-255
[30] Ding W, Chang B. Improving Chinese Semantic Role Classification with Hierarchical Feature Selection Strategy[C]. Proceedings of the Conference on Empirical Methods in Natural Language Processing(EMNLP), 2008:324-323
[31] Zhao H, Chen W L, Kit C. Semantic Dependency Parsing of NomBank and PropBank: An Efficient Integrated Approach via a Large-scale Feature Selection[C]. Proceedings of the Conference on Empirical Methods in Natural Language Processing(EMNLP), Singapore, 2009:30-39
[32] Boxwell S A, Dennis M D, Brew C. Brutus: A Semantic Role Labeling System Incorporating CCG, CFG, and Dependency Features[C]. Proceedings of the 47th Annual Meeting of the ACL and the 4th IJCNLP of the AFNLP, Singapore, 2009:37-45
[33] Swier R S, Stevenson S. Unsupervised Semantic Role Labelling[C]. Proceedings of the Conference on Empirical Methods in Natural Language Processing(EMNLP), 2004:95-102
[34] Fuerstenau H and Lapata M. Graph Alignment for Semi-Supervised Semantic Role Labeling[C]. Proceedings of the Conference on Empirical Methods in Natural Language Processing(EMNLP), 2009:11-20
[35] Abend, O, Rappoport, A. Fully Unsupervised Core-Adjunct Argument Classification[C]. Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics(ACL), 2010:226-236
[36] Swier R S, Stevenson S. Exploiting a Verb Lexicon in Automatic Semantic Role Labelling[C]. Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing (HLT/EMNLP), 2005:883-890
[37] Grenager T, Manning C D. Unsupervised Discovery of a Statistical Verb Lexicon[C]. Proceedings of the Conference on Empirical Methods in Natural Language Processing(EMNLP), 2006:1-8
[38] Poon H, Domingos P. Unsupervised Semantic Parsing[C]. Proceedings of the Conference on Empirical Methods in Natural Language Processing(EMNLP), 2009:1-10
[39] Abend O, Reichart R, Rappoport A. Unsupervised Argument Identification for Semantic Role Labeling[C]. Proceedings of the 47th Annual Meeting of the ACL and the 4th IJCNLP of the AFNLP, 2009:28-36
[40] Deschacht K, Moens M F. Semi-supervised Semantic Role Labeling Using the Latent Words Language Model[C]. Proceedings of the Conference on Empirical Methods in Natural Language Processing(EMNLP), 2009:21-29
[41] Moschitti A. A Study on Convolution Kernels for Shallow Statistic Parsing[C]. Proceedings of the 42th Annual Meeting of the Association for Computational Linguistics(ACL), 2004:335-342
[42] Moschitti A, Basili R. Verb subcategorization kernels for automatic semantic labeling[C]. Proceedings of the ACL-05 Workshop on Deep Lexical Acquisition, 2005:10-17
[43] Collins M, Duffy N. Convolution kernels for natural language[J]. In Advances in Neural Information Processing Systems(NIPS), 2001, 14(1):625--632.
[44] Che W X, Zhang M, Aw A T, et al. Using a Hybrid Convolution Tree Kernel for Semantic Role Labeling[J]. ACM Transactions on Asian Language Information Processing, 2008, 7(4):1-23
[45] Zhang M, Che W X, Aw A T, et al. A Grammar-driven Convolution Tree Kernel for Semantic Role Classification[C]. Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics (ACL), 2007:200-207
[46] Sun H, Jurafsky D. Shallow Semantic Parsing of Chinese[C]. Proceedings of the Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics(HLT-NAACL), 2004:249-256
[47] Xue N, Palmer M. Automatic Semantic Role Labeling for Chinese Verbs[C]. In Proceedings of International Joint Conferences on Artificial Intelligence (IJCAI), 2005:1160-1165.
[48] Sun W. Improving Chinese Semantic Role Labeling with Rich Syntactic Features[C]. Proceedings of the 48th Annual Meeting of the Association of Computational Linguistics (ACL), 2010:168-172
[49]安强强,张蕾.基于依存树的中文语义角色标注[J].计算机工程. 2010, 4:161-164
[50]董振东,董强,郝长伶.知网的理论发现[J].中文信息学报, 2007,(21)4:3-9
[51]王步康,王红玲,袁晓虹等.基于依存句法分析的中文语义角色标注[J].中文信息学报, 2010, 24(1):25-30
[52]李军辉,周国栋,朱巧明等.中文名词性谓词语义角色标注研究[J].软件学报, 2010
[53]丁伟伟,常宝宝.基于语义组块分析的汉语语义角色标注[J].中文信息学报, 2009, 23(5):53-62
[54]邵艳秋,穗志方,吴云芳.基于词汇语义特征的中文语义角色标注研究[J].中文信息学报, 2009, 6:3-10
[55]车万翔.基于核方法的语义角色标注研究[D].哈尔滨:哈尔滨工业大学, 2008.
[56]李济洪.汉语框架语义角色的自动标注技术研究[D].太原:山西大学, 2010.
[57]王红玲.基于特征向量的中英文语义角色标注研究[D].苏州:苏州大学, 2009.
[58]刘怀军,车万翔,刘挺.中文语义角色标注的特征工程[J].中文信息学报. 2007, 21(1):80-84
[59]丁金涛,王红玲,周国栋等.语义角色标注中特征优化组合研究[J].计算机应用与软件, 2009, 5
[60]刘娜.中文特殊句式的语义角色标注[D].北京:北京邮电大学, 2009.
[61] Johansson R, Williams D, Berglund A, et al. Carsim: A System to Visualize Written Road Accident Reports as Animated 3D Scenes[C]. In Hirst, G. and Nirenburg, S., editors, ACL2004: Second Workshop on Text Meaning and Interpretation, Barcelona, Spain, 2004, 57-64
[62]陆汝钤,张松懋.从故事到动画片——全过程计算机辅助动画自动生成[J].自动化学报, 2002, 28(3):322-348
[63] Carreras X, Màrquez L. Introduction to the CoNLL-2004 Shared Task: Semantic Role Labeling[C]. Proceedings of the Conference on Computational Natural Language Learning (CoNLL), 2004
[64] Carreras X, Màrquez L. Introduction to the CoNLL-2005 Shared Task: Semantic Role Labeling[C]. Proceedings of the Conference on Computational Natural Language Learning (CoNLL), 2005
[65] Surdeanu M, Johansson R, Meyers A, et al. The CoNLL-2008 Shared Task on Joint Parsing of Syntactic and Semantic Dependencies[C]. Proceedings of the Conference on Computational Natural Language Learning (CoNLL), 2008
[66] Hajic J, Ciaramita M, Johansson R, et al. The CoNLL-2009 Shared Task: Joint Parsing of Syntactic and Semantic Dependencies in Multiple Languages[C]. Proceedings of the Conference on Computational Natural Language Learning (CoNLL), 2009
[67] Litkowski K C. Senseval-3 task: Automatic Labeling of Semantic Roles[C]. Proceedings of the 4th International Workshop on Semantic Evaluations (SensEval), 2004:99-104
[68] Baker C, Ellsworth M, Erk K. SemEval-2007 Task 19: Frame semantic Structure Extraction[C]. Proceedings of the 4th International Workshop on Semantic Evaluations (SemEval), ACL, 2007:99-104
[69] Zhou Q. SemEval-2010 task 11: Event Detection in Chinese News Sentences[C]. Proceedings of the 5th International Workshop on Semantic Evaluation (SemEval), ACL, 2010:86
[70] Hacioglu K. Semantic Role Labeling Using Dependency Trees[C]. Proceedings of the International Conference on Computational Linguistics (COLING), 2004:1273-1276
[71] Koomen P, Punyakanok V, Roth D, et al. Generalized Inference with Multiple Semantic Role Labeling Systems[C]. Proceedings of the 9th Conference on Computational Natural Language Learning (CoNLL), 2005:181-184
[72] Roth D. Learning to Resolve Natural Language Ambiguities: A Unified Approach[C]. Proceedings of the Fifteenth National Conference on Artificial Intelligence (AAAI) and Tenth Conference on Innovative Applications of Artificial Intelligence (IAAI), Menlo Park, CA, USA, 1998:806-813
[73] Johansson R, Nugues P. Dependency-based Syntactic-Semantic Analysis with PropBank and NomBank[C]. Proceedings of the 12th Conference on Computational Natural Language Learning (CoNLL), 2008:183-187
[74] Crammer K, Dekel O, Keshet J, et al. Online Passive-aggressive Algorithms[J]. Journal of Machine Learning Research, 2006, (7):551-585
[75] Lin C J, Weng R C, Keerthi S S. Trust Region Newton Method for Large-scale Logistic Regression[J]. Journal of Machine Learning Research, 2008, (9):627-650
[76] Zhang Y, Wang R, Uszkoreit H. Hybrid Learning of Dependency Structures from Heterogeneous Linguistic Resources[C]. Proceedings of the Conference on Computational Natural Language Learning (CoNLL), 2008:198-202
[77] McDonald R, Pereira F, Ribarov K, et al. Non-Projective Dependency Parsing using Spanning Tree Algorithms[C]. In Proceedings of HLT-EMNLP, Vancouver, Canada, 2005:523-530,
[78] Nivre J, Nilsson J, Hall J, et al. Maltparser: A Language-independent System for Data-driven Dependency Parsing[J]. Natural Language Engineering, 2007, 13(1):1-41.
[79] Zhao H, Chen W, Kazama J, et al. Multilingual Dependency Learning: Exploiting Rich Features for Tagging Syntactic and Semantic Dependencies[C]. Proceedings of the 13th Conference on Computational Natural Language Learning (CoNLL), 2009:61-66
[80] Che W, Li Z, Li Y, et al. Multilingual Dependency-based Syntactic and Semantic Parsing[C]. Proceedings of the 13th Conference on Computational Natural Language Learning (CoNLL), 2009:49-54
[81] Ngai G, Wu D, Carpuat M, et al. Semantic Role Labeling with Boosting, SVMs,Maximum Entropy, SNOW, and Decision Lists[C]. Proceedings of SensEval-3, ACL, 2004
[82] Johansson R, Nugues P. Using WordNet to Extend FrameNet Coverage[C]. Proceedings of SemEval-2007, ACL, 2007
[83]王厚峰.汉语篇章的指代消解浅论[J].语言文字应用, 2004, 4: 113-119
[84]孔芳,周国栋,朱巧明等.指代消解综述[J].计算机工程, 2010,36(8):33-36
[85] Cardie C, Wagstaff K. Noun Phrase Coreference as Clustering[C]. Proceedings of the Joint Conference on Empirical Methods in Natural Language Processing and Very Large Corpora, Maryland, USA, 1999:82-89
[86] Bergler S, Witte R, Khalife M, et al. Using Knowledge-Poor Coreference Resolution for Text Summarization[C]. Proceedings of the HLT-NAACL Workshop on Text Summarization. Edmonton, Canada, 2003:85-92
[87] Bean D, Riloff E. Unsupervised Learning of Contextual Role Knowledge for Coreference Resolution[C]. Proceedings of HLT-NAACL, Boston, USA. 2004: 297-304
[88] Wang C S, Ngai G. A Clustering Approach for Unsupervised Chinese Coreference Resolution[C]. Proceedings of the 5th SIGHAN Workshop on Chinese Language Processing, Sydney, Australia, 2006:40-46
[89]周俊生,黄书剑.一种基于图划分的无监督汉语指代消解算法[J].中文信息学报, 2007, 21(2):77-82
[90] Xu R, Wunsch D. Survey of Clustering Algorithm[J]. IEEE Transactions on Neural Networks, 2005:645-678
[91] Quinlan J R. Induction of Decision Trees[J]. Machine Learning, 1986, 1:81-106
[92] Quinlan J R. C4.5: Programs for Machine Learning[M]. San Mateo, CA: Morgan Kaufmann, 1993
[93] Linguistic Data Consortium. ACE (Automatic Content Extraction) Chinese Annotation Guidelines for Entities Version 5.5[S]. University of Pennsylvania, Philadelphia, USA. 2005.
[94] Hsu C W, Lin C J. A Comparison of Methods for Multi-class Support Vector Machines[J]. IEEE transactions on Neural Networks, 2002, 13(2):415-425
[95] Carpenter G A, Grossberg S. A Massively Parallel Architecture for a Self-organizing Neural Pattern Recognition Machine[J]. Computer Vision, Graphics, and Image Process, 1987, 37(1): 54-115
[96] Vilain M, Burger J, Aberdeen J, et al. A Model Theoretic Coreference Scoring Scheme[C]. Proceedings of the 6th Message Understanding Conference, Morgan Kaufmann, San Francisco, 1995: 45-52
[97] Joachims T. Making large-Scale SVM Learning Practical. Advances in KernelMethods[J]. Support Vector Learning, B. Sch?lkopf and C. Burges and A. Smola (ed.), MIT Press, 1998.
[98] Luo X. On Coreference Resolution Performance Metrics[C]. Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing, Vancouver, Canada, 2005:25-32
[99] Carreras X, Marquez L. Introduction to the CoNLL-2005 Shared Task: Semantic Role Labeling[C]. Proceedings of the Conference on Computational Natural Language Learning (CoNLL), 2005:152-164
[100] Pradhan S, Ward W, Martin J H. Towards Robust Semantic Role Labeling[J]. Computational Linguistics, 2008, 34(2):289-310
[101] Pradhan S, Hacioglu K, Krugler V, et al. Support Vector Learning for Semantic Argument Classification[J]. Machine Learning Journal, 2005,60(3):11-39
[102] Pradhan S, Waed W, Haciolgu K, et al. Shallow Semantic Parsing using Support Vector Machines[C]. Proceedings of HLT-NAACL, 2004:233-240
[103] Marneffe M C, MacCartney B, Manning C D. Generating Typed Dependency Parses from Phrase Structure Parses[C]. Proceedings of the International Conference on Language Resources and Evaluation (LREC), 2006:449-454
[104] Duda R O, Hart P E, Stork D G. Pattern Classification[M]. 2nd Edition. New York: John Wiley, 2001
[105] Levy R, Manning C D. Is It Harder to Parse Chinese, or the Chinese Treebank[C]. Proceedings of the 41st Annual Meeting on Association for Computational Linguistics (ACL), 2003:439-446
[106] Florian R, Ittycheriah A, Jing H, et al. Named Entity Recognition through Classifier Combination[C]. Proceedings of the Conference on Computational Natural Language Learning (CoNLL), 2003:168-171
[107] Lu X, Wang Y, Jain A K. Combining Classifiers for Face Recognition[C]. Proceedings of IEEE International Conference on Multimedia and Expo, 2003:13-16
[108] Jordan M I, Xu L. Convergence Results for the EM Approach to Mixtures of Experts Architectures[J]. Neural Networks, 1995, (8):1409-1431
[109] Xu L, Jordan M I. On Convergence Properties of the EM Algorithm for Guassian Mixtures[J]. Neural Computation, 1996, 8(1):129-151.
[110] Cover T M, Hart P E. Nearest Neighbor Pattern Classification[J]. IEEE Transactions on Information Theory, 1967,13(1): 21-27
[111] Hall P, Park B U, Samworth R J. Choice of Neighbor Order in Nearest-neighbor Classification[J]. Annals of Statistics, 2008,36(5):2135-2152
[112] Breslow L A, Aha D W. Simplifying Decision Trees: a Survey[J]. KnowledgeEngineering Review, 1997, 12(1):1-40
[113] Breiman L, Friedman J H, Olshen R, et al. Classification and Regression Trees[M]. Monterey, CA:Wadsworth and Brooks, 1983
[114] Quinlan J R. Learning Efficient Classification Procedures and Their Application to Chess End Games[J]. Machine Learning: An Artificial Intelligence Approach, Palo Alto, CA, 1983
[115] Rosenblatt F. The Perceptron: A Probabilistic Model for Information Storage and Organization in the Brain[J], Cornell Aeronautical Laboratory, Psychological Review, 1958, 65(6):386-408.
[116] Gallant S I. Perceptron-based Learning Algorithms[J]. IEEE Transactions on Neural Networks, 1990,1(2):179-191.
[117] Park K M, Rim H C. Maximum Entropy Based Semantic Role Labeling[C]. Proceedings of the Conference on Computational Natural Language Learning (CoNLL), 2005:209-212
[118]刘挺,车万翔,李生.基于最大熵分类器的语义角色标注[J].软件学报, 2007, 18(3):565-573
[119] Shannon C E. A Mathematical Theory of Communication[J]. Bell System Technical Journal, 1948, (27):379-423,623-656
[120] Guiasu S, Shenitzer, A. The Principle of Maximum Entropy[J]. The Mathematical Intelligencer, 1985, 7(1):42-48.
[121] Zhang L. Maximum Entropy Modeling Toolkit for Python and C++[EB/OL]. http://homepages.inf.ed.ac.uk/lzhang10/maxent_toolkit.html, 2006
[122] Vapnik V, Kotz S. Estimation of Dependences Based on Empirical Data[M]. New York:Springer, 2006
[123] Sun R. The Cambridge Handbook of Computational Psychology[M]. Cambridge University Press, 2008
[124] Laird J E, Newwell A, Rosenbloom P S. Soar: An Architecture for General Intelligence[J]. Artificial Intelligence, 1987, 33(3):1-64
[125] Laird J E, Hucka M, et al. An Analysis of Soar as an Integrated Architecture[J]. ACM SIGART Bulletin, 1991, 2(4):98-103
[126] Benjamin D, Lonsdale D, Lyons D. A Cognitive Robotics Approach to Comprehending Human Language and Behaviors[C]. Proceeding of the ACM/ IEEE International Conference on Human-Robot Interaction, 2007:185-192
[127] Anderson J R, Lebiere C. The Atomic Components of Thought[M]. Mahwah, NJ:Lawrence Erlbaum Associates, 1998
[128] Anderson J R. Cognitive Psychology and Its Implications[M]. New York: WH Freeman and Company, 1999
[129] McClelland J L. Connectionist Models and Psychological Evidence[J]. Journal of Memory and Language, 1988, 27:107-123
[130] Rumelhart D E. The Architecture of Mind: A Connectionist Approach[J]. Foundations of Cognitive Science, Cambridge:Bradford Books, 1989:133-159
[131] Miikkulainen R. Text and Discourse Understanding: The DISCERN System[J]. AHandbook of Natural Language Processing: Techniques and Applications for the Processing of Language as Text. New York: Marcel Dekker, 1999
[132] Brown D P, Tepper J A, Powell H M. Connectionist Natural Language Parsing[J]. Trends in Cognitive Sciences, 2002
[133] Scholtes J C. Neural Networks in Natural Language Processing and Information Retrieval[D]. Netherlands:Universiteit van Amsterdam, 1993
[134] Moisl H. Artificial Neural Networks and Natural Language Processing[J]. Encyclopedia of Library and Information Science, 2003
[135] Kintsch W. The Role of Knowledge in Discourse Comprehension: A Construction and Integration Model[J]. Psychological Review, 1988, 95:163-182
[136] Collins A M, Loftus E F. A Spreading Activation Theory of Semantic Processing[J]. Psychological Review, 1975, 82(6):407-428
[137] Kintsch W. Comprehension: A Paradigm for Cognition[M]. Cambridge University Press, 1998
[138] Kapusuz E. Refining the Representational Basis of the Construction-Integration Model of Text Comprehension with Syntactic Cues[D]. Turkey: Middle East Technical University, 2001
[139] Mueller E T. Story Understanding[J]. Encyclopedia of Cognitive Science, London: Macmillan Reference, 2002
[140] Nuar P. Computing versus Human Thinking[J]. Communications of the ACM, 2007, 50(1):85-94
[141] Kintsch W. The Role of Knowledge in Discourse Comprehension: a Constru-ction and Integration Model[J]. Psychological Review, 1988, 95(2):163-182
[142] Guha A, Rossi J P. Convergence of the Integration Dynamics of the Construction-Integration Model[J]. Journal of Mathematical Psychology, 2001, 45:355-369
[143] Sanjose V, Abarca E V, Padilla O M. A Connectionist Extension to Kintsch’s Construction-Integration Model[J]. Discourse Processes, 2006, 42(1):1-35
[144] Zhu X, Ghahramani Z. Learning from Labeled and Unlabeled Data with Label Propagation[R]. Pittsburgh:Carnegie Mellon University, CMU-CALD-02-107, 2002.
[2] Shen D, Lapata M. Using Semantic Roles to Improve Question Answering[C]. Proceedings of the Joint Conference on Empirical Methods in Natural Language Processing (EMNLP) and Computational Natural Language Learning (CoNLL), 2007:12-21
[3] Bilotti M W, Ogilvie P, Callan J, et al. Structured Retrieval for Question Answering[C]. In Proceedings of the 30th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, New York, USA, 2007:351-358
[4] Fillmore C J, Baker C F. Frame Semantics for Text Understanding[C]. Proceedings of the North American Chapter of the Association for Computational Linguistics (NACCL) 2001 Workshop on WordNet and Other Lexical Resources, Pittsburgh, 2001
[5] Liu D, Gildea. Semantic Role Features for Machine Translation[C]. Proceedings of the 23rd International Conference on Computational Linguistics (COLING), 2010:716-724
[6] Adorni G, Manzo M D, Giunchiglia F. Natural Language Driven Image Generation[C]. Proceedings of the International Conference on Computational Linguistics(COLING). Stanford, California, 1984:495-500
[7] Coyne B, Sproat R. WordsEye: An Automatic Text-to-Scene Conversion System[C]. Proceedings of the Annual Conference on Computer Graphics, Los Angeles, USA, 2001:487-496
[8] Gruber J S. Studies in Lexical Relations[D]. Ph.D. Dissertation, Massachusetts Institute of Technology (MIT), 1965
[9] Fillmore C J. The Case for Case. In Bach and Harms (eds.): Universals in Linguistic Theory[M]. New York:Holt, Rinehart and Winston, 1968:1-88
[10] Chomsky N. Lectures on Government and Binding[M]. Dordrecht:Foris, 1981
[11] Gildea D, Palmer M. The Necessity of Syntactic Parsing for Predicate Argument Recognition[C]. Proceedings of the Association for Computational Linguistics(ACL), 2002:239-246
[12] Punyakanok V, Roth S, Yih W. The Necessity of Syntactic Parsing for Semantic Role Labeling[C]. Proceedings of International Joint Conferences on Artificial Intelligence (IJCAI). 2005: 1117-1123
[13] Baker C F, Fillmore C J, Lowe J B. The Berkeley FrameNet Project[J]. Proceedings of COLING-ACL’98 Joint Conference, 1998:86-90
[14] Kipper K, Korhonen A, Ryant N, et al. A Large-scale Classification of English Verbs[J]. Language Resources and Evaluation, 2008, (42):21-40
[15] Palmer M, Gildea D, Kingsbury P. The Proposition Bank: An Annotated Corpus of Semantic Roles[J]. Computational Linguistics, 2005, 31(1):71-106
[16] Meyers A, Reeves R, Macleod C, et al. Annotating Noun Argument Structure for NomBank[C]. Proceedings of the International Conference on Language Resources and Evaluation(LREC), 2004:803-806
[17]刘开瑛,由丽萍.汉语框架语义知识库构建工程[C].中文信息处理前沿进展——中国中文信息学会成立二十五周年学术会议论文集, 2006, (11):64-71
[18]周强.汉语句法语义链接知识库开发[C].第八届汉语词汇语义学研讨会. 2007
[19] Xue N, Palmer M. Adding Semantic Roles to the Chinese Treebank[J]. Natural Language Engineering, 2009, 15(1):143-172
[20] Xue N, Palmer M. Annotating the Propositions in the Penn Chinese Treebank[C]. Proceedings of the Second SIGHAN Workshop on Chinese Language Processing, 2003:47-54
[21] Xue N, Palmer M. Calibrating Features for Semantic Role Labeling[C]. Proceedings of the Conference on Empirical Methods in Natural Language Processing(EMNLP), 2004:88-94
[22] Toutanova K. Haghighi A, Manning C M. A Global Joint Model for Semantic Role Labeling[J]. Computational Linguistics, 2008, 34(2):161-191
[23] Mitchell T M. Machine Learning[M]. New York: McGraw-Hill, 1997
[24]李军辉.中文句法语义分析及其联合学习机制研究[D].苏州:苏州大学, 2010, 27
[25] Gildea D, Jurafsky D. Automatic Labeling of Semantic Roles[J]. Computational Linguistics, 2002, 28(3):245-288
[26] Chen J, Rambow O. Use of Deep Linguistic Features for the Recognition and Labeling of Semantic Arguments[C]. Proceedings of the Conference on Empirical Methods in Natural Language Processing(EMNLP), 2004, 41-48
[27] Surdeanu M, Harabagiu S, Williams J, et al. Using Predicate-argument Structures for Information Extraction[C]. In Proceedings of the Annual Meeting of the Association for Computational Linguistics(ACL), 2003:8-15
[28] Pradhan S, Hacioglu K, Krugler V, et al. Support vector learning for semantic argument classification[J]. Machine Learning Journal, 2005, 60(3):11-39
[29] Xue N. Labeling Chinese Predicates with Semantic Roles[J]. Computational Linguistics, 2008, 34(2):225-255
[30] Ding W, Chang B. Improving Chinese Semantic Role Classification with Hierarchical Feature Selection Strategy[C]. Proceedings of the Conference on Empirical Methods in Natural Language Processing(EMNLP), 2008:324-323
[31] Zhao H, Chen W L, Kit C. Semantic Dependency Parsing of NomBank and PropBank: An Efficient Integrated Approach via a Large-scale Feature Selection[C]. Proceedings of the Conference on Empirical Methods in Natural Language Processing(EMNLP), Singapore, 2009:30-39
[32] Boxwell S A, Dennis M D, Brew C. Brutus: A Semantic Role Labeling System Incorporating CCG, CFG, and Dependency Features[C]. Proceedings of the 47th Annual Meeting of the ACL and the 4th IJCNLP of the AFNLP, Singapore, 2009:37-45
[33] Swier R S, Stevenson S. Unsupervised Semantic Role Labelling[C]. Proceedings of the Conference on Empirical Methods in Natural Language Processing(EMNLP), 2004:95-102
[34] Fuerstenau H and Lapata M. Graph Alignment for Semi-Supervised Semantic Role Labeling[C]. Proceedings of the Conference on Empirical Methods in Natural Language Processing(EMNLP), 2009:11-20
[35] Abend, O, Rappoport, A. Fully Unsupervised Core-Adjunct Argument Classification[C]. Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics(ACL), 2010:226-236
[36] Swier R S, Stevenson S. Exploiting a Verb Lexicon in Automatic Semantic Role Labelling[C]. Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing (HLT/EMNLP), 2005:883-890
[37] Grenager T, Manning C D. Unsupervised Discovery of a Statistical Verb Lexicon[C]. Proceedings of the Conference on Empirical Methods in Natural Language Processing(EMNLP), 2006:1-8
[38] Poon H, Domingos P. Unsupervised Semantic Parsing[C]. Proceedings of the Conference on Empirical Methods in Natural Language Processing(EMNLP), 2009:1-10
[39] Abend O, Reichart R, Rappoport A. Unsupervised Argument Identification for Semantic Role Labeling[C]. Proceedings of the 47th Annual Meeting of the ACL and the 4th IJCNLP of the AFNLP, 2009:28-36
[40] Deschacht K, Moens M F. Semi-supervised Semantic Role Labeling Using the Latent Words Language Model[C]. Proceedings of the Conference on Empirical Methods in Natural Language Processing(EMNLP), 2009:21-29
[41] Moschitti A. A Study on Convolution Kernels for Shallow Statistic Parsing[C]. Proceedings of the 42th Annual Meeting of the Association for Computational Linguistics(ACL), 2004:335-342
[42] Moschitti A, Basili R. Verb subcategorization kernels for automatic semantic labeling[C]. Proceedings of the ACL-05 Workshop on Deep Lexical Acquisition, 2005:10-17
[43] Collins M, Duffy N. Convolution kernels for natural language[J]. In Advances in Neural Information Processing Systems(NIPS), 2001, 14(1):625--632.
[44] Che W X, Zhang M, Aw A T, et al. Using a Hybrid Convolution Tree Kernel for Semantic Role Labeling[J]. ACM Transactions on Asian Language Information Processing, 2008, 7(4):1-23
[45] Zhang M, Che W X, Aw A T, et al. A Grammar-driven Convolution Tree Kernel for Semantic Role Classification[C]. Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics (ACL), 2007:200-207
[46] Sun H, Jurafsky D. Shallow Semantic Parsing of Chinese[C]. Proceedings of the Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics(HLT-NAACL), 2004:249-256
[47] Xue N, Palmer M. Automatic Semantic Role Labeling for Chinese Verbs[C]. In Proceedings of International Joint Conferences on Artificial Intelligence (IJCAI), 2005:1160-1165.
[48] Sun W. Improving Chinese Semantic Role Labeling with Rich Syntactic Features[C]. Proceedings of the 48th Annual Meeting of the Association of Computational Linguistics (ACL), 2010:168-172
[49]安强强,张蕾.基于依存树的中文语义角色标注[J].计算机工程. 2010, 4:161-164
[50]董振东,董强,郝长伶.知网的理论发现[J].中文信息学报, 2007,(21)4:3-9
[51]王步康,王红玲,袁晓虹等.基于依存句法分析的中文语义角色标注[J].中文信息学报, 2010, 24(1):25-30
[52]李军辉,周国栋,朱巧明等.中文名词性谓词语义角色标注研究[J].软件学报, 2010
[53]丁伟伟,常宝宝.基于语义组块分析的汉语语义角色标注[J].中文信息学报, 2009, 23(5):53-62
[54]邵艳秋,穗志方,吴云芳.基于词汇语义特征的中文语义角色标注研究[J].中文信息学报, 2009, 6:3-10
[55]车万翔.基于核方法的语义角色标注研究[D].哈尔滨:哈尔滨工业大学, 2008.
[56]李济洪.汉语框架语义角色的自动标注技术研究[D].太原:山西大学, 2010.
[57]王红玲.基于特征向量的中英文语义角色标注研究[D].苏州:苏州大学, 2009.
[58]刘怀军,车万翔,刘挺.中文语义角色标注的特征工程[J].中文信息学报. 2007, 21(1):80-84
[59]丁金涛,王红玲,周国栋等.语义角色标注中特征优化组合研究[J].计算机应用与软件, 2009, 5
[60]刘娜.中文特殊句式的语义角色标注[D].北京:北京邮电大学, 2009.
[61] Johansson R, Williams D, Berglund A, et al. Carsim: A System to Visualize Written Road Accident Reports as Animated 3D Scenes[C]. In Hirst, G. and Nirenburg, S., editors, ACL2004: Second Workshop on Text Meaning and Interpretation, Barcelona, Spain, 2004, 57-64
[62]陆汝钤,张松懋.从故事到动画片——全过程计算机辅助动画自动生成[J].自动化学报, 2002, 28(3):322-348
[63] Carreras X, Màrquez L. Introduction to the CoNLL-2004 Shared Task: Semantic Role Labeling[C]. Proceedings of the Conference on Computational Natural Language Learning (CoNLL), 2004
[64] Carreras X, Màrquez L. Introduction to the CoNLL-2005 Shared Task: Semantic Role Labeling[C]. Proceedings of the Conference on Computational Natural Language Learning (CoNLL), 2005
[65] Surdeanu M, Johansson R, Meyers A, et al. The CoNLL-2008 Shared Task on Joint Parsing of Syntactic and Semantic Dependencies[C]. Proceedings of the Conference on Computational Natural Language Learning (CoNLL), 2008
[66] Hajic J, Ciaramita M, Johansson R, et al. The CoNLL-2009 Shared Task: Joint Parsing of Syntactic and Semantic Dependencies in Multiple Languages[C]. Proceedings of the Conference on Computational Natural Language Learning (CoNLL), 2009
[67] Litkowski K C. Senseval-3 task: Automatic Labeling of Semantic Roles[C]. Proceedings of the 4th International Workshop on Semantic Evaluations (SensEval), 2004:99-104
[68] Baker C, Ellsworth M, Erk K. SemEval-2007 Task 19: Frame semantic Structure Extraction[C]. Proceedings of the 4th International Workshop on Semantic Evaluations (SemEval), ACL, 2007:99-104
[69] Zhou Q. SemEval-2010 task 11: Event Detection in Chinese News Sentences[C]. Proceedings of the 5th International Workshop on Semantic Evaluation (SemEval), ACL, 2010:86
[70] Hacioglu K. Semantic Role Labeling Using Dependency Trees[C]. Proceedings of the International Conference on Computational Linguistics (COLING), 2004:1273-1276
[71] Koomen P, Punyakanok V, Roth D, et al. Generalized Inference with Multiple Semantic Role Labeling Systems[C]. Proceedings of the 9th Conference on Computational Natural Language Learning (CoNLL), 2005:181-184
[72] Roth D. Learning to Resolve Natural Language Ambiguities: A Unified Approach[C]. Proceedings of the Fifteenth National Conference on Artificial Intelligence (AAAI) and Tenth Conference on Innovative Applications of Artificial Intelligence (IAAI), Menlo Park, CA, USA, 1998:806-813
[73] Johansson R, Nugues P. Dependency-based Syntactic-Semantic Analysis with PropBank and NomBank[C]. Proceedings of the 12th Conference on Computational Natural Language Learning (CoNLL), 2008:183-187
[74] Crammer K, Dekel O, Keshet J, et al. Online Passive-aggressive Algorithms[J]. Journal of Machine Learning Research, 2006, (7):551-585
[75] Lin C J, Weng R C, Keerthi S S. Trust Region Newton Method for Large-scale Logistic Regression[J]. Journal of Machine Learning Research, 2008, (9):627-650
[76] Zhang Y, Wang R, Uszkoreit H. Hybrid Learning of Dependency Structures from Heterogeneous Linguistic Resources[C]. Proceedings of the Conference on Computational Natural Language Learning (CoNLL), 2008:198-202
[77] McDonald R, Pereira F, Ribarov K, et al. Non-Projective Dependency Parsing using Spanning Tree Algorithms[C]. In Proceedings of HLT-EMNLP, Vancouver, Canada, 2005:523-530,
[78] Nivre J, Nilsson J, Hall J, et al. Maltparser: A Language-independent System for Data-driven Dependency Parsing[J]. Natural Language Engineering, 2007, 13(1):1-41.
[79] Zhao H, Chen W, Kazama J, et al. Multilingual Dependency Learning: Exploiting Rich Features for Tagging Syntactic and Semantic Dependencies[C]. Proceedings of the 13th Conference on Computational Natural Language Learning (CoNLL), 2009:61-66
[80] Che W, Li Z, Li Y, et al. Multilingual Dependency-based Syntactic and Semantic Parsing[C]. Proceedings of the 13th Conference on Computational Natural Language Learning (CoNLL), 2009:49-54
[81] Ngai G, Wu D, Carpuat M, et al. Semantic Role Labeling with Boosting, SVMs,Maximum Entropy, SNOW, and Decision Lists[C]. Proceedings of SensEval-3, ACL, 2004
[82] Johansson R, Nugues P. Using WordNet to Extend FrameNet Coverage[C]. Proceedings of SemEval-2007, ACL, 2007
[83]王厚峰.汉语篇章的指代消解浅论[J].语言文字应用, 2004, 4: 113-119
[84]孔芳,周国栋,朱巧明等.指代消解综述[J].计算机工程, 2010,36(8):33-36
[85] Cardie C, Wagstaff K. Noun Phrase Coreference as Clustering[C]. Proceedings of the Joint Conference on Empirical Methods in Natural Language Processing and Very Large Corpora, Maryland, USA, 1999:82-89
[86] Bergler S, Witte R, Khalife M, et al. Using Knowledge-Poor Coreference Resolution for Text Summarization[C]. Proceedings of the HLT-NAACL Workshop on Text Summarization. Edmonton, Canada, 2003:85-92
[87] Bean D, Riloff E. Unsupervised Learning of Contextual Role Knowledge for Coreference Resolution[C]. Proceedings of HLT-NAACL, Boston, USA. 2004: 297-304
[88] Wang C S, Ngai G. A Clustering Approach for Unsupervised Chinese Coreference Resolution[C]. Proceedings of the 5th SIGHAN Workshop on Chinese Language Processing, Sydney, Australia, 2006:40-46
[89]周俊生,黄书剑.一种基于图划分的无监督汉语指代消解算法[J].中文信息学报, 2007, 21(2):77-82
[90] Xu R, Wunsch D. Survey of Clustering Algorithm[J]. IEEE Transactions on Neural Networks, 2005:645-678
[91] Quinlan J R. Induction of Decision Trees[J]. Machine Learning, 1986, 1:81-106
[92] Quinlan J R. C4.5: Programs for Machine Learning[M]. San Mateo, CA: Morgan Kaufmann, 1993
[93] Linguistic Data Consortium. ACE (Automatic Content Extraction) Chinese Annotation Guidelines for Entities Version 5.5[S]. University of Pennsylvania, Philadelphia, USA. 2005.
[94] Hsu C W, Lin C J. A Comparison of Methods for Multi-class Support Vector Machines[J]. IEEE transactions on Neural Networks, 2002, 13(2):415-425
[95] Carpenter G A, Grossberg S. A Massively Parallel Architecture for a Self-organizing Neural Pattern Recognition Machine[J]. Computer Vision, Graphics, and Image Process, 1987, 37(1): 54-115
[96] Vilain M, Burger J, Aberdeen J, et al. A Model Theoretic Coreference Scoring Scheme[C]. Proceedings of the 6th Message Understanding Conference, Morgan Kaufmann, San Francisco, 1995: 45-52
[97] Joachims T. Making large-Scale SVM Learning Practical. Advances in KernelMethods[J]. Support Vector Learning, B. Sch?lkopf and C. Burges and A. Smola (ed.), MIT Press, 1998.
[98] Luo X. On Coreference Resolution Performance Metrics[C]. Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing, Vancouver, Canada, 2005:25-32
[99] Carreras X, Marquez L. Introduction to the CoNLL-2005 Shared Task: Semantic Role Labeling[C]. Proceedings of the Conference on Computational Natural Language Learning (CoNLL), 2005:152-164
[100] Pradhan S, Ward W, Martin J H. Towards Robust Semantic Role Labeling[J]. Computational Linguistics, 2008, 34(2):289-310
[101] Pradhan S, Hacioglu K, Krugler V, et al. Support Vector Learning for Semantic Argument Classification[J]. Machine Learning Journal, 2005,60(3):11-39
[102] Pradhan S, Waed W, Haciolgu K, et al. Shallow Semantic Parsing using Support Vector Machines[C]. Proceedings of HLT-NAACL, 2004:233-240
[103] Marneffe M C, MacCartney B, Manning C D. Generating Typed Dependency Parses from Phrase Structure Parses[C]. Proceedings of the International Conference on Language Resources and Evaluation (LREC), 2006:449-454
[104] Duda R O, Hart P E, Stork D G. Pattern Classification[M]. 2nd Edition. New York: John Wiley, 2001
[105] Levy R, Manning C D. Is It Harder to Parse Chinese, or the Chinese Treebank[C]. Proceedings of the 41st Annual Meeting on Association for Computational Linguistics (ACL), 2003:439-446
[106] Florian R, Ittycheriah A, Jing H, et al. Named Entity Recognition through Classifier Combination[C]. Proceedings of the Conference on Computational Natural Language Learning (CoNLL), 2003:168-171
[107] Lu X, Wang Y, Jain A K. Combining Classifiers for Face Recognition[C]. Proceedings of IEEE International Conference on Multimedia and Expo, 2003:13-16
[108] Jordan M I, Xu L. Convergence Results for the EM Approach to Mixtures of Experts Architectures[J]. Neural Networks, 1995, (8):1409-1431
[109] Xu L, Jordan M I. On Convergence Properties of the EM Algorithm for Guassian Mixtures[J]. Neural Computation, 1996, 8(1):129-151.
[110] Cover T M, Hart P E. Nearest Neighbor Pattern Classification[J]. IEEE Transactions on Information Theory, 1967,13(1): 21-27
[111] Hall P, Park B U, Samworth R J. Choice of Neighbor Order in Nearest-neighbor Classification[J]. Annals of Statistics, 2008,36(5):2135-2152
[112] Breslow L A, Aha D W. Simplifying Decision Trees: a Survey[J]. KnowledgeEngineering Review, 1997, 12(1):1-40
[113] Breiman L, Friedman J H, Olshen R, et al. Classification and Regression Trees[M]. Monterey, CA:Wadsworth and Brooks, 1983
[114] Quinlan J R. Learning Efficient Classification Procedures and Their Application to Chess End Games[J]. Machine Learning: An Artificial Intelligence Approach, Palo Alto, CA, 1983
[115] Rosenblatt F. The Perceptron: A Probabilistic Model for Information Storage and Organization in the Brain[J], Cornell Aeronautical Laboratory, Psychological Review, 1958, 65(6):386-408.
[116] Gallant S I. Perceptron-based Learning Algorithms[J]. IEEE Transactions on Neural Networks, 1990,1(2):179-191.
[117] Park K M, Rim H C. Maximum Entropy Based Semantic Role Labeling[C]. Proceedings of the Conference on Computational Natural Language Learning (CoNLL), 2005:209-212
[118]刘挺,车万翔,李生.基于最大熵分类器的语义角色标注[J].软件学报, 2007, 18(3):565-573
[119] Shannon C E. A Mathematical Theory of Communication[J]. Bell System Technical Journal, 1948, (27):379-423,623-656
[120] Guiasu S, Shenitzer, A. The Principle of Maximum Entropy[J]. The Mathematical Intelligencer, 1985, 7(1):42-48.
[121] Zhang L. Maximum Entropy Modeling Toolkit for Python and C++[EB/OL]. http://homepages.inf.ed.ac.uk/lzhang10/maxent_toolkit.html, 2006
[122] Vapnik V, Kotz S. Estimation of Dependences Based on Empirical Data[M]. New York:Springer, 2006
[123] Sun R. The Cambridge Handbook of Computational Psychology[M]. Cambridge University Press, 2008
[124] Laird J E, Newwell A, Rosenbloom P S. Soar: An Architecture for General Intelligence[J]. Artificial Intelligence, 1987, 33(3):1-64
[125] Laird J E, Hucka M, et al. An Analysis of Soar as an Integrated Architecture[J]. ACM SIGART Bulletin, 1991, 2(4):98-103
[126] Benjamin D, Lonsdale D, Lyons D. A Cognitive Robotics Approach to Comprehending Human Language and Behaviors[C]. Proceeding of the ACM/ IEEE International Conference on Human-Robot Interaction, 2007:185-192
[127] Anderson J R, Lebiere C. The Atomic Components of Thought[M]. Mahwah, NJ:Lawrence Erlbaum Associates, 1998
[128] Anderson J R. Cognitive Psychology and Its Implications[M]. New York: WH Freeman and Company, 1999
[129] McClelland J L. Connectionist Models and Psychological Evidence[J]. Journal of Memory and Language, 1988, 27:107-123
[130] Rumelhart D E. The Architecture of Mind: A Connectionist Approach[J]. Foundations of Cognitive Science, Cambridge:Bradford Books, 1989:133-159
[131] Miikkulainen R. Text and Discourse Understanding: The DISCERN System[J]. AHandbook of Natural Language Processing: Techniques and Applications for the Processing of Language as Text. New York: Marcel Dekker, 1999
[132] Brown D P, Tepper J A, Powell H M. Connectionist Natural Language Parsing[J]. Trends in Cognitive Sciences, 2002
[133] Scholtes J C. Neural Networks in Natural Language Processing and Information Retrieval[D]. Netherlands:Universiteit van Amsterdam, 1993
[134] Moisl H. Artificial Neural Networks and Natural Language Processing[J]. Encyclopedia of Library and Information Science, 2003
[135] Kintsch W. The Role of Knowledge in Discourse Comprehension: A Construction and Integration Model[J]. Psychological Review, 1988, 95:163-182
[136] Collins A M, Loftus E F. A Spreading Activation Theory of Semantic Processing[J]. Psychological Review, 1975, 82(6):407-428
[137] Kintsch W. Comprehension: A Paradigm for Cognition[M]. Cambridge University Press, 1998
[138] Kapusuz E. Refining the Representational Basis of the Construction-Integration Model of Text Comprehension with Syntactic Cues[D]. Turkey: Middle East Technical University, 2001
[139] Mueller E T. Story Understanding[J]. Encyclopedia of Cognitive Science, London: Macmillan Reference, 2002
[140] Nuar P. Computing versus Human Thinking[J]. Communications of the ACM, 2007, 50(1):85-94
[141] Kintsch W. The Role of Knowledge in Discourse Comprehension: a Constru-ction and Integration Model[J]. Psychological Review, 1988, 95(2):163-182
[142] Guha A, Rossi J P. Convergence of the Integration Dynamics of the Construction-Integration Model[J]. Journal of Mathematical Psychology, 2001, 45:355-369
[143] Sanjose V, Abarca E V, Padilla O M. A Connectionist Extension to Kintsch’s Construction-Integration Model[J]. Discourse Processes, 2006, 42(1):1-35
[144] Zhu X, Ghahramani Z. Learning from Labeled and Unlabeled Data with Label Propagation[R]. Pittsburgh:Carnegie Mellon University, CMU-CALD-02-107, 2002.