中文功能组块分析及应用研究
|
摘要
近年来,中文自然语言处理技术在分词、词性标注等方面获得了很大进步。然而,自然语言处理应用系统(如信息抽取、问答系统等)则需要对文本信息进行深层解释。功能组块分析任务为句子成分自动标注主语、宾语、时间状语、地点状语等功能标记,作为语法分析及语义理解的一种实现方式,具有定义清晰、便于评价等优点,近年来受到越来越多学者的关注。
本文提出基于序列判别模型的中文功能组块自动分析技术,将传统的支持向量机分类模型扩展到序列学习任务中,灵活地使用了输入输出序列之间的多重相依特征。研究表明,本文提出的方法获得目前中文功能组块分析的最好性能,系统整体F1值达到93.76,并且可以较好地扩展到不同的特征集合,适合于众多自然语言处理问题。
论文的第一部分说明了功能组块分析的几个问题:课题的提出与研究及意义,相关研究现状,以及本论文的研究重点。然后简要介绍了本课题采用的语料库资源——宾夕法尼亚大学中文树库,讨论了中文功能组块的划分标准。接着,以自然语言理解的全信息方法论为基础,分析了功能组块标记在语法、语义、语用理解中的位置及作用。最后说明了几个常用的考察组块标记性能的指标。
论文的第二部分详细介绍了本研究的理论基础,具体说明了序列判别模型在中文功能组块识别中的应用。在对算法模型进行分析的基础上,构建了中文功能组块自动标注器,并通过大量实验,从多方面分析了系统的性能,检验了不同特征对于系统性能的影响及其语言学解释。接着,比较了两个不同的构建功能组块标注器的方法:采用简单词法信息(词、词性等)的标注器和采用完全句法树信息(短语类型、句法树路径等)的标注器,并通过实验说明了基于词法信息的功能组块标注器具有性能稳定、领域适应能力强等优点,适用于缺少句法资源或句法分析本身存在困难的语言,是进行汉语功能组块分析的有效方法。
论文的第三部分介绍了功能组块标记在自然语言处理系统中的应用。我们选取文本观点挖掘中的观点要素识别为应用领域,以句子成分的功能类别为依据,构建了观点主题自动识别系统,并通过实验验证了该方法的可行性。最后,给出了本研究的结论以及未来的研究方向。
以上工作不仅实现了汉语功能组块自动分析系统,并且从计算语言学的角度,对汉语功能组块进行了明确界定,对其它相关的应用研究具有参考价值。目前的实验结果也显示了功能组块分析技术具有非常好的应用前景。
As researchers improve results on various other problems in "pure" natural language processing (e.g. part-of-speech tagging, parsing), those who work in the more "applied" NLP fields (e.g. question-answering, information extraction) are seeking more powerful sorts of linguistic annotation as input for their own systems. Function tags are a context-sensitive annotation applied to words and phrases of natural language text, marking their syntactic or semantic role within a larger utterance.
In this thesis we develop a sequential predication model for Chinese function tag labeling. We will show that this method provides state-of-the-art accuracy, yielding an F1 score of 93.76, is extensible through the feature set and can be implemented efficiently. Furthermore, we display the specific properties of Chinese function tags by comparing it with English as well as show its practical applicability through integration into an opinion holder recognition system.
In the first part of the thesis, we present the problem of function tag labeling: why it is an interesting problem, who else has worked on similar thing, and what exactly we intend to do. Then we will briefly review the datasets we are working on - the Penn Chinese Treebank, and explain the specific metrics by which we will evaluate our work.
In the second part of the thesis, we will present a sequential predication model. This will lead to the heart of the thesis - automatic function tag labeling. Here we formulate function tag labeling as a sequence learning problem within structural spaces, yielding state-of-the-art accuracy and high robustness. Then we will present an analysis of what features prove to be the most helpful for Chinese function tag assignment and why we think it will be useful in this task, and introduce two totally different function labeling systems, one assigning function tags to unparsed text using simple lexical features (word, part-of-speech tag, etc), and one assigning function tags to the output of parsed text using features collected from the full parsed trees (phrase type, tree path, etc). We then discuss the advantages and disadvantages of each system in various situations . We also compare our function tagger to other state-of-the-art systems.
Finally, in the third part of the thesis, we present how this work improves the applications of text opinion mining. We will introduce our primary work on opinion holder recognition by using function tags as clues, to show its applicability to a real world problem. Lastly, we will present a comparison to other systems performing related tasks, and speculate on some interesting future work.
The proposed work has defined Chinese function tags from the view of computation and yielded an automatic Chinese funtion tag labeler. The research results are directive and with reference value to other related work. In addition, the experiment suggests the promising application of function tags.
本文提出基于序列判别模型的中文功能组块自动分析技术,将传统的支持向量机分类模型扩展到序列学习任务中,灵活地使用了输入输出序列之间的多重相依特征。研究表明,本文提出的方法获得目前中文功能组块分析的最好性能,系统整体F1值达到93.76,并且可以较好地扩展到不同的特征集合,适合于众多自然语言处理问题。
论文的第一部分说明了功能组块分析的几个问题:课题的提出与研究及意义,相关研究现状,以及本论文的研究重点。然后简要介绍了本课题采用的语料库资源——宾夕法尼亚大学中文树库,讨论了中文功能组块的划分标准。接着,以自然语言理解的全信息方法论为基础,分析了功能组块标记在语法、语义、语用理解中的位置及作用。最后说明了几个常用的考察组块标记性能的指标。
论文的第二部分详细介绍了本研究的理论基础,具体说明了序列判别模型在中文功能组块识别中的应用。在对算法模型进行分析的基础上,构建了中文功能组块自动标注器,并通过大量实验,从多方面分析了系统的性能,检验了不同特征对于系统性能的影响及其语言学解释。接着,比较了两个不同的构建功能组块标注器的方法:采用简单词法信息(词、词性等)的标注器和采用完全句法树信息(短语类型、句法树路径等)的标注器,并通过实验说明了基于词法信息的功能组块标注器具有性能稳定、领域适应能力强等优点,适用于缺少句法资源或句法分析本身存在困难的语言,是进行汉语功能组块分析的有效方法。
论文的第三部分介绍了功能组块标记在自然语言处理系统中的应用。我们选取文本观点挖掘中的观点要素识别为应用领域,以句子成分的功能类别为依据,构建了观点主题自动识别系统,并通过实验验证了该方法的可行性。最后,给出了本研究的结论以及未来的研究方向。
以上工作不仅实现了汉语功能组块自动分析系统,并且从计算语言学的角度,对汉语功能组块进行了明确界定,对其它相关的应用研究具有参考价值。目前的实验结果也显示了功能组块分析技术具有非常好的应用前景。
As researchers improve results on various other problems in "pure" natural language processing (e.g. part-of-speech tagging, parsing), those who work in the more "applied" NLP fields (e.g. question-answering, information extraction) are seeking more powerful sorts of linguistic annotation as input for their own systems. Function tags are a context-sensitive annotation applied to words and phrases of natural language text, marking their syntactic or semantic role within a larger utterance.
In this thesis we develop a sequential predication model for Chinese function tag labeling. We will show that this method provides state-of-the-art accuracy, yielding an F1 score of 93.76, is extensible through the feature set and can be implemented efficiently. Furthermore, we display the specific properties of Chinese function tags by comparing it with English as well as show its practical applicability through integration into an opinion holder recognition system.
In the first part of the thesis, we present the problem of function tag labeling: why it is an interesting problem, who else has worked on similar thing, and what exactly we intend to do. Then we will briefly review the datasets we are working on - the Penn Chinese Treebank, and explain the specific metrics by which we will evaluate our work.
In the second part of the thesis, we will present a sequential predication model. This will lead to the heart of the thesis - automatic function tag labeling. Here we formulate function tag labeling as a sequence learning problem within structural spaces, yielding state-of-the-art accuracy and high robustness. Then we will present an analysis of what features prove to be the most helpful for Chinese function tag assignment and why we think it will be useful in this task, and introduce two totally different function labeling systems, one assigning function tags to unparsed text using simple lexical features (word, part-of-speech tag, etc), and one assigning function tags to the output of parsed text using features collected from the full parsed trees (phrase type, tree path, etc). We then discuss the advantages and disadvantages of each system in various situations . We also compare our function tagger to other state-of-the-art systems.
Finally, in the third part of the thesis, we present how this work improves the applications of text opinion mining. We will introduce our primary work on opinion holder recognition by using function tags as clues, to show its applicability to a real world problem. Lastly, we will present a comparison to other systems performing related tasks, and speculate on some interesting future work.
The proposed work has defined Chinese function tags from the view of computation and yielded an automatic Chinese funtion tag labeler. The research results are directive and with reference value to other related work. In addition, the experiment suggests the promising application of function tags.
引文
[118]Magerman D M.Statistical decision-tree models for parsing[C]//Anon.Proceedings of the 33rd ACL,Cambridge,Massachusetts,USA:276-283.
[119]Charniak E.Statistical parsing with a context-free grammar and word statistics[C]//Anon.Proceedings of the 14th AAAI,Menlo Park,CA,USA:598-603.
[120]Ratnaparkhi A.Learning to parse natural language with maximum entropy models[J].Machine learning.1999,34(1-3):151-175.
[121]Charniak E.A Maximum-Entropy-Inspired Parser[C]//Anon.Proceedings of the 1st Manual Meeting of the NAACL,Seattle,WA,USA:132-139.
[122]Marcus M,Kim G,Marcinkiewicz M A,et al.The Penn Treebank:Annotating predicate argument structure[C]//Anon.Proceedings of ARPA Human Language Technology Workshop,San Francisco,USA.
[123]Martha Palmer D G,Kingsbury P.The Proposition Bank:An annotated corpus of semantic roles [J].Computational Linguistics.2005,31(1):71-106.
[124]Lowe J B,Baker C F,Fillmore C J.A frame-semantic approach to semantic annotation[C]//Anon.Proceedings of the SIGLEX workshop "Tagging Text with Lexical Semantics:Why,What,and How?",Washington,D.C.,USA.
[125]Xue N,Xia F,Huang S,et al.The Bracketing Guidelines for the Chinese Treebank[R].[S.1.]:[s.n.],2000.
[126]钟义信.自然语言理解的全信息方法论[J].北京邮电大学学报.2004,27(4):1-12.
[127]钟义信.信息科学原理(第三版)[M].[S.1.]:北京邮电大学出版社,2002.
[128]Blaheta D,Charniak E.Assigning Function Tags to Parsed Text[C]//Anon.Proceedings of the 1st NAACL,Seattle,WA,USA:234-240.
[129]Blaheta D.Function tagging[D].[S.1.]:Brown University,2004.
[130]Medo P,Musillo G.Accurate Function Parsing[C]//Anon.Proceedings of EMNLP 2005,Vancouver,Canada:620-627.
[131]Gildea D,Palmer M.The Necessity of Parsing for Predicate Argument Recognition[C]//Anon.Proceedings of the 40th ACL,Philadelphia,USA:239-246.
[132]周强,赵颖泽.汉语功能块自动分析[J].中文信息学报.2007,21.
[133]Newell A.Unitied Theories of Cognition[M].[S.1.]:Harvard University Press,1994.
[134]Abney S.Principle-Based Parsing[M].[S.1.]:Kluwer Academic Publishers,1991:257-278.
[135]Sang T K,Buchholz S.Introduction to the CoNLL-2000 Shared Task:Chunking[C]//Anon.Proceedings of CoNLL-2000 and LLL-2000,Lisbon,Portugal:127-132.
[136]Yamada H,Matsumoto Y.Statistical dependency analysis with support vector machines[C]//Anon.Proceedings of the 8th International Workshop on Parsing Technologies(IWPT),Nancy,France:195-206.
[137]Jijkoun V,d Rijke M.Enriching the output of a parser using memory-based learning[C]//Anon.Proceedings of the 42nd ACL,Barcelona,Spain:311-318.
[138]Kipper K,Dang H T,Palmer M.Class based construction of a verb lexicon[C]//Anon.Proceedings of the 17th National Conference on Artificial Intelligence(AAAI-2000),Austin,Texas.USA:691-696.
[139]Gildea D,Jurafsky D.Automatic Labeling of Semantic Roles[J].Computational Linguistics.2002,28(3):1-45.
[140]Levin B.English Verb Classes and Alternations:A Preliminary Investigation[M].[S.1.]:The University of Chicago Press,1993.
[141]Swier R,Stevenson S.Unsupervised semantic role labelling[C]//Anon.Proceedings of EMNLP-2004,Barcelona,Spain:95-102.
[142]Iida R,Komachi M,Inui K,et al.Annotating a Japanese Text Corpus with Predicate-Argument and Coreference Relations[C]//Anon.Proceedings of ACL Workshop on The Linguistic Annotation.Prague,Czech Republic:132-139.
[143]周强.詹卫东,任海波.构建大规模的汉语语块库(M].[S.1.]:清华大学出版社:自然语言理解与机器翻译,2001.
[144]Drabek E F,Zhou Q.Experiments in learning models for functional chunking of Chinese text[C]//Anon.Proceedings of IEEE NLP-KE 2001,Tucson,AZ,USA:859-864.
[145]陈亿,周强.宇航.分层次的汉语功能块描述库构建分析[J].中文信息学报.2008.22.
[146]Zhao Y,Zhou Q.A SVM-based Model for Chinese Functional Chunk Parsing[C]//Anon.Proceedings of the Fifth SIGHAN Workshop on Chinese Language Processing,Sydney,Australia:94-101.
[147]俞士汶,朱学锋.受限汉语研究的必要性[M].[S.1.]:《语言现代化论从》第三集,南开大学出版社,1997.
[148]Collins M.Head-Driven Statistical Models for Natural Language Parsing[D].[S.1.]:University of Pennsylvania,1999.
[149]Lafferty J,McCallum A,Pereira F.Conditional random fields:probabilistic models for segmenting and labeling sequence data[C]//Anon.Proceedings of the International Conference on Machine Learning,Williamstown,USA:282-289.
[150]Mcdonald R,Pereira F.Online learning of approximate dependency parsing algorithms[C]//Anon.Proceedings of the EACL 2006:81-88.
[151]Berger A,Pietra D S,Pietra D V.A maximum entropy approach to natural language processing [J].Computational Linguistics.1996,22(1):39-71.
[152]Surdeanu M,Johansson R,Meyers A,et al.The CoNLL 2008 Shared Task on Joint Parsing of Syntactic and Semantic Dependencies[C]//Anon.Proceedings of the CoNLL-2008,Manchester,UK:159-177.
[153]Altun Y,Tsochantaridis I,Hofmann T.Hidden Markov Support Vector Machines[C]//Anon.Proceedings of ICML 2003,Washington,DC,USA:172-188.
[154]Tsochantaridis T,Hofmann T,Joachims T,et al.Support Vector Machine Learning for Interdependent and Structured Output Spaces[C]//Anon.Proceedings of ICML 2004,Banff,Canada:823-830.
[155]Preiss J.Using grammatical relations to compare parsers[C]//Anon.Proceedings of the 10th Conference of the European Chapter of the ACL,Budapest,Hungary:291-298.
[156]Merit P,Ferrer E E.The Notion of Argument in Prepositional Phrase Attachment[J].Computational Linguistics.2006,32(3):341-378.
[157]Bethard S,Yu H,Thornton A,et al.Automatic Extraction of Opinion Propositions and their Holders [C]//Anon.Proceedings of AAAI Spring Symposium on Exploring Attitude and Affect in Text:Theories and Applications,Stanford University,USA.
[158]周强.汉语语料库的短语自动划分和标注研究[D].[S.1.]:北京大学,2002.
[159]Kiss T,Strunk J.Unsupervised multilingual sentence boundary detection[J].Computational Linguistics.2002,32(4):485-525.
[160]王小捷,常宝宝.自然语言处理技术基础[M].[S.1.]:北京:北京邮电大学出版社,2002.
[161] Manning C D, Schuetze H. Foundations of statistical natural language processing [M]. [S. 1.]: MIT Press, 1999.
[162] 林杏光.现代汉语动词大词典[M]. [S. 1.]:北京语言学院出版社, 1994.
[163] Taskar B, Guestrin C, Koller D. Max-margin Markov networks [C] // Anon. Advances in Neural Information Processing Systems 16, Cambridge, MA.
[164] Tsochantaridis I, Joachims T, Hofmann T, et al. Large Margin Methods for Structured and Interdependent Output Variables [J]. The Journal of Machine Learning Research. 2005, 6: 1453-1484.
[165] Joachims T. A support vector method for multivariate performance measures [C] // Anon. Proceedings of International Conference on Machine Learning, Bonn, Germany: 377-384.
[166] Tikhonov A N. Solution of incorrectly formulated problems and the regularization method [J].Soviet Math. Dokl. 1963: 1035-1038.
[167] Jurafsky D, Martin J H. Speech and Language Processing: An Introduction to Natural Language Processing, Speech Recognition, and Computational Linguistics [M]. [S. 1.]: Prentice-Hall, 2000.
[168] Durbin R, Eddy S, Krogh A, et al. Biological Sequence Analysis: Probabilistic Models of Proteins and Nucleic Acids [M]. [S. 1.]: Cambridge University Press, 1998.
[169] Dietterich T G. Machine learning for sequential data: A review [C] // Anon. Proceedings of the Joint IAPR International Workshop on Structural, Syntactic, and Statistical Pattern Recognition:15-30.
[170] Rabiner L. A Tutorial on Hidden Markov Models and Selected Applications in Speech Recognition [C] // Anon. Proceedings of the IEEE: 257-286.
[171] Juang B, Rabiner L. Hidden Markov models for speech recognition [J]. Technometrics. 1991, 22:251-272.
[172] Mccallum A, Freitag D, Pereira F. Maximum Entropy Markov Models for Information Extraction and Segmentation [C| // Anon. Proceedings of ICML 2000, Stanford University, USA: 591-598.
[173] Collins M. Ranking algorithms for named-entity extraction: Boosting and the voted perceptron [C]// Anon. Proceedings of the 40nd ACL, Philadelphia, Pennsylvania, USA: 489-496.
[174] Collins M, Roark B. Incremental parsing with the perceptron algorithm [C] // Anon. Proceedings of the 42nd ACL.
[1751 Jordan M I. Serial order: A parallel distributed processing approach [R]. [S. 1.]: [s. n.]. 1987.
[176] Lafferty J, Zhu X, Liu Y. Kernel conditional random fields: representation and clique selection [C]// Anon. Proceedings of the International Conference on Machine Learning.
[177]Nguyen N,Guo Y.Comparisonsof sequence labeling algorithms and extensions[C]//Anon.Proceedings of ICML 2007,Corvalis,Oregon:681-688.
[178]Ratsch G,Sonnenburg S.Large scale hidden semi-Markov SVMs[C]//Anon.Proceedings of the Advances in Neural Information Processing Systems.
[179]Vapnik V.Statistical Learning Theory[M].[S.1.]:Wiley,1998.
[180]Bottou L,Cortes C,Denker J,et al.Comparison of classifier methods:A case study in handwriting digit recognition[C]//Anon.Proceedings of International Conference on Pattern Recognition,Jerusalem,Israel:77-87.
[181]Kressel U.Pairwise classification and support vector machines[J].Advances in Kernel Methods-Support Vector Learning.1999.
[182]Weston J,Watkins C.Multi-class support vector machines[R].[S.1.]:[s.n.],1998.
[183]Crammer K,Singer Y.On the algorithmic implementation of multiclass kernel-based vector machines [J].Journal of Machine Learning Research.2001:265-292.
[184]Schwarz R,Chow Y L.The n-best algorithm:An efficient and exact procedure for finding the N most likely hypotheses[C]//Anon.Proceedings of the IEEE International Conference on Acoustics,Speech and Signal Processing:81-84.
[185]Taskar B,Guestrin C,Koller D.Max Margin markov networks[C]//Anon.Proceedings of Advances in neural information processing systems.
[186]Platt J C.Using analytic QP and sparseness to speed training of support vector machines[C]//Anon.Proceedings of Advances in neural information processing systems:557563.
[187]Xue N.Labeling Chinese Predicates with Semantic Roles[J].Computational Linguistics.2005,34(2):225-255.
[188]Che W,Zhang M,Liu T,et al.A Hybrid Convolution Tree Kernel for Semantic Role Labeling[C]//Anon.Proceedings of the 21st International Conference on Computational Linguistics and the 44th ACL,Sydney,Australia:73-80.
[189]朱德熙.语法讲义[M].[S.1.]:商务印书馆,1982.
[190]张华平,刘群.基于N-最短路径方法的中文词语粗分模型[J].中文信息学报.2002,16(5):77-84.
[191]Gao J,Li M,Huang C-N.Improved source-channel models for Chinese word segmentation[C]//Anon.Proceedings of the 41st ACL,Sapporo,Japan:7-12.
[192]刘群,张华平,俞鸿魁,et al.基于层叠隐马模型的汉语词法分析[J].计算机研究与发展.2004,41(8):1421-1429.
[193]张亮,黄河燕,胡春玲.基于Multigram语言模型的主动学习中文分词[J].中文信息学报.2006,20(1):50-58.
[194]Zhang H,Yu H,Xiong D,et al.HHMM-based Chinese Lexical Analyzer ICTCLAS[C]//Anon.Proceedings of Second SIGHAN workshop affiliated with 41th ACL,Sapporo,Japan:184-187.
[195]Qin Y,Yuan C,Sun J,et al.BUPT Systems in the SIGHAN Bakeoff 2007[C]//Anon.Proceedings of the Sixth SIGHAN Workshop on Chinese Language Processing,Hyderabad,India:94-97.
[196]陈小荷.现代汉语自动分析[M].[S.1.]:北京:北京语言文化大学出版社,2000.
[197]Gao J,Wu A,Li M,et al.Adaptive Chinese Word Segmentation[C]//Anon.Proceedings of the 42nd ACL,Barcelona,Spain:311-318.
[198]屈刚,陆汝占.一个改进的汉语词性标注系统[J].上海交通大学学报.2003,37(6):897-900.
[199]张孝飞,陈肇雄,黄河燕,et al.词性标注中生词处理算法研究[J].中文信息学报.2003,17(5):1-5.
[200]Yuan C,Wang X,Zhong Y.Some improvements on maximum entropy based Chinese POS tagging [J].THEJOURNAL OF CHINA UNIVERSITIES OF POSTS AND TELECOMMUNICATIONS.2004,13(13):14-18.
[201]Wang M,Sagae K,Mitamura T.A Fast,Accurate Deterministic Parser for Chinese[C]//Anon.Proceedings of the the 44th ACL,Sydney,Australia:425-432.
[202]Forman G.An extensive empirical study of feature selection metrics for text classification[J].Journal of Machine Learning Research:Special Issue on Variable and Feature Selection.2003:1289-1305.
[203]Wiebe J M,Wilson T,Bruce R F,et al.Learning subjective language[J].ComputationalLinguistics.2004,30(3):277-308.
[204]Gamon M,Aue A.Development and use of a gold standard data set for subjectivity classifications [C]//Anon.Proceedings of Workshop on Sentiment and Subjectivity in Text of COLING/ACL 2006.
[205]Turney P D.Thumbs up or thumbs down? Semantic orientation applied to unsupervised classification of reviews[C]//Anon.Proceedings of the 40th ACL,Philadelphia,Pennsylvania:417-424.
[206]Hu M,Liu B.Mining and summarizing customer reviews[C]//Anon.Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery & Data Mining(KDD-2004),Seattle,WA,USA:168-177.
[207]Ku L-W,Chen H-H.Mining Opinions from the Web:Beyond Relevance Retrieval[J].Journal of American Society for Information Science and Technology,Special Issue on Mining Web Resources for Enhancing Information Retrieval.2000,58(12):1838-1850.
[208]董静,王万森.E-learning系统中情感识别的研究[J].计算机工程与设计.2008,29(17):4525-4534.
[209]T Wilson J W,Hoffmann P.Recognizing contextual polarity in phrase-level sentiment analysis[C]//Anon.Proceedings of the HLT/EMNLP 2005.
[210]Kim S-M,Eduard H.Identifying Opinion Holders for Question Answering in Opinion Texts[C]//Anon.Proceedings of AAAI-05 Workshop on Question Answering in Restricted Domains,Pittsburgh,USA.
[211]Pang B,Lee L,Vaithyanathan S.Thumbs up? Sentiment Classification using Machine Learning Techniques[C]//Anon.Proceedings of EMNLP 2002,San Jose,CA,USA:79-86.
[212]Somasundaran S,Wiebe J,Ruppenhofer J.Discourse Level Opinion Interpretation[C]//Anon.Proceedings of the 22nd International Conference on Computational Linguistics(COLING-2008),Manchester,UK.
[213]Choi Y,Cardie C,Riloff E,et al.Identifying sources of opinions with conditional random fields and extraction patterns[C]//Anon.Proceedings of the HLT/EMNLP 2005.
[214]Seki Y,Evans D K,Ku L-W,et al.Overview of Opinion Analysis Pilot Task at NTCIR-6[C]//Anon.Proceedings of NTCIR-6 Workshop Meeting,Tokyo,Japan:265-278.
[215]Xu R,Wong K-F,Xia Y.Opinmine-Opinion Analysis System by CUHK for NTCIR-6 Pilot Task [C]//Anon.Proceedings of NTCIR-6 Workshop Meeting,Tokyo,Japan:350-357.
[216]Li Y,Bontcheva K,Cunningham H.Experiments of Opinion Analysis on the Corpora MPQA and NTCIR-6[C]//Anon.Proceedings of NTCIR-6 Workshop Meeting,Tokyo,Japan:323-329.
[217]Huang R,Sun L,Pan L.ISCAS in Opinion Analysis Pilot Task:Experiments with sentimental dictionary based classifier and CRF model[C]//Anon.Proceedings of NTCIR-6 Workshop Meeting,Tokyo,Japan:296-300.
[218]Ku L-W,Lo Y-S,Chen H-H.Using Opinion Scores of Words for Sentence-Level Opinion Extraction [C]//Anon.Proceedings of NTCIR-6 Workshop Meeting,Tokyo,Japan:316-322.
[219]Wu Y,Oard D.NTCIR-6 at Maryland:Chinese Opinion Analysis Pilot Task[C]//Anon.Proceedings of NTCIR-6 Workshop Meeting,Tokyo,Japan:344-349.
[220]Stoyanov V,Cardie C.Annotating Topics of Opinions[C]//Anon.Proceedings of the Sixth International Language Resources and Evaluation(LREC'08),Marrakech,Morocco.
[221]史树敏,黄河燕,刘东升.自然语言文本共指消解性能评测算法研究[J].计算机科学.2008,35(9):168-177.
[222]Xue N.Annotation Guidelines for the Penn Chinese Proposition Bank(1st Draft)[R].[S.1.]:[s.n.],2007.
[223]Yuan C,Wang X,Zhong Y.Some Improvements on Maximum Entropy based Chinese POS Tagging [J].The Journal of China Universities of Posts and Telecommunications.2006:99-103.
[224]Yuan C,Wang X,Ren F,et al.Function Labeling for Unparsed Chinese Text[J].IEEJ Transactions on Electronics,Information and Systems,Section C,Japan.2009.(Accepted).
[225]Yuan C,Ren F.Accurate Learning for Chinese Function Tags from Lexical Evidence[J].Chinese Journal of Electronics.2009.(Accepted).
[226]Yuan C,Ren F,Wang X.Accuracy Learning for Chinese Function Tags from Minimal Features [C]//Anon.Proceedings of the ACL-IJCNLP 2009 Student Research Workshop.
[227]Yuan C,Wang X,Ren F,et al.Exploiting Lexical Information for Function Tag Labeling[C]//Anon.Proceedings of the IEEE NLP-KE'08,Beijing,China:67-74.
[228]Qin Y,Yuan C,Sun J.et al.BUPT Systems in the SIGHAN Bakeoff 2007[C]//Anon.Proceedings of the Sixth SIGHAN Workshop on Chinese Language Processing,Hyderabad,India:94-97.
[229]Cai J,Yuan C,Wang X,et al.Semantic Role Labeling for Multi-VP Clauses in Chinese[C]//Anon.Proceedings of the IEEE NLP-KE'07,Beijing,China:367-372.
[230]Yuan C,Wang C.Parsing Model for Answer Extraction in Chinese Question Answering System [C]//Anon.Proceedings of the IEEE NLP-KE'05,Wuhan,China:206-211.
[231]Yuan C.Wang J,Wang C.The Web-based Domain Independent DM for Intelligent Spoken Dialog System[C]//Anon.Proceedings of the IEEE Networking,Sensing and Control Proceedings,Arizona,USA:1027-1030.
[232]Yuan C,Yu L,Sun X,et al.Assigning Function Tags to Unparsed Text[C]//Anon.2008 International Symposium on Artificial and Affective Computing/AIAC-08),Tokushima.Japan:189-200.
[233]Yuan C,Ren F.Predicate-Argument Annotating for Unparsed Text[C]//Anon.2008 Shikokusection Joint Convention of the Institutes of Electrical and related Engineers.Tokushima,Japan.
[234]Yuan C,Wang X.Semi-supervised Maximum Entropy Based POS Tagging for Large Scale Chinese Corpus[C]//Anon.Proceedings of the 3rd Students' Workshop on Computational Linguistics,Shenyang,China:99-104.
[119]Charniak E.Statistical parsing with a context-free grammar and word statistics[C]//Anon.Proceedings of the 14th AAAI,Menlo Park,CA,USA:598-603.
[120]Ratnaparkhi A.Learning to parse natural language with maximum entropy models[J].Machine learning.1999,34(1-3):151-175.
[121]Charniak E.A Maximum-Entropy-Inspired Parser[C]//Anon.Proceedings of the 1st Manual Meeting of the NAACL,Seattle,WA,USA:132-139.
[122]Marcus M,Kim G,Marcinkiewicz M A,et al.The Penn Treebank:Annotating predicate argument structure[C]//Anon.Proceedings of ARPA Human Language Technology Workshop,San Francisco,USA.
[123]Martha Palmer D G,Kingsbury P.The Proposition Bank:An annotated corpus of semantic roles [J].Computational Linguistics.2005,31(1):71-106.
[124]Lowe J B,Baker C F,Fillmore C J.A frame-semantic approach to semantic annotation[C]//Anon.Proceedings of the SIGLEX workshop "Tagging Text with Lexical Semantics:Why,What,and How?",Washington,D.C.,USA.
[125]Xue N,Xia F,Huang S,et al.The Bracketing Guidelines for the Chinese Treebank[R].[S.1.]:[s.n.],2000.
[126]钟义信.自然语言理解的全信息方法论[J].北京邮电大学学报.2004,27(4):1-12.
[127]钟义信.信息科学原理(第三版)[M].[S.1.]:北京邮电大学出版社,2002.
[128]Blaheta D,Charniak E.Assigning Function Tags to Parsed Text[C]//Anon.Proceedings of the 1st NAACL,Seattle,WA,USA:234-240.
[129]Blaheta D.Function tagging[D].[S.1.]:Brown University,2004.
[130]Medo P,Musillo G.Accurate Function Parsing[C]//Anon.Proceedings of EMNLP 2005,Vancouver,Canada:620-627.
[131]Gildea D,Palmer M.The Necessity of Parsing for Predicate Argument Recognition[C]//Anon.Proceedings of the 40th ACL,Philadelphia,USA:239-246.
[132]周强,赵颖泽.汉语功能块自动分析[J].中文信息学报.2007,21.
[133]Newell A.Unitied Theories of Cognition[M].[S.1.]:Harvard University Press,1994.
[134]Abney S.Principle-Based Parsing[M].[S.1.]:Kluwer Academic Publishers,1991:257-278.
[135]Sang T K,Buchholz S.Introduction to the CoNLL-2000 Shared Task:Chunking[C]//Anon.Proceedings of CoNLL-2000 and LLL-2000,Lisbon,Portugal:127-132.
[136]Yamada H,Matsumoto Y.Statistical dependency analysis with support vector machines[C]//Anon.Proceedings of the 8th International Workshop on Parsing Technologies(IWPT),Nancy,France:195-206.
[137]Jijkoun V,d Rijke M.Enriching the output of a parser using memory-based learning[C]//Anon.Proceedings of the 42nd ACL,Barcelona,Spain:311-318.
[138]Kipper K,Dang H T,Palmer M.Class based construction of a verb lexicon[C]//Anon.Proceedings of the 17th National Conference on Artificial Intelligence(AAAI-2000),Austin,Texas.USA:691-696.
[139]Gildea D,Jurafsky D.Automatic Labeling of Semantic Roles[J].Computational Linguistics.2002,28(3):1-45.
[140]Levin B.English Verb Classes and Alternations:A Preliminary Investigation[M].[S.1.]:The University of Chicago Press,1993.
[141]Swier R,Stevenson S.Unsupervised semantic role labelling[C]//Anon.Proceedings of EMNLP-2004,Barcelona,Spain:95-102.
[142]Iida R,Komachi M,Inui K,et al.Annotating a Japanese Text Corpus with Predicate-Argument and Coreference Relations[C]//Anon.Proceedings of ACL Workshop on The Linguistic Annotation.Prague,Czech Republic:132-139.
[143]周强.詹卫东,任海波.构建大规模的汉语语块库(M].[S.1.]:清华大学出版社:自然语言理解与机器翻译,2001.
[144]Drabek E F,Zhou Q.Experiments in learning models for functional chunking of Chinese text[C]//Anon.Proceedings of IEEE NLP-KE 2001,Tucson,AZ,USA:859-864.
[145]陈亿,周强.宇航.分层次的汉语功能块描述库构建分析[J].中文信息学报.2008.22.
[146]Zhao Y,Zhou Q.A SVM-based Model for Chinese Functional Chunk Parsing[C]//Anon.Proceedings of the Fifth SIGHAN Workshop on Chinese Language Processing,Sydney,Australia:94-101.
[147]俞士汶,朱学锋.受限汉语研究的必要性[M].[S.1.]:《语言现代化论从》第三集,南开大学出版社,1997.
[148]Collins M.Head-Driven Statistical Models for Natural Language Parsing[D].[S.1.]:University of Pennsylvania,1999.
[149]Lafferty J,McCallum A,Pereira F.Conditional random fields:probabilistic models for segmenting and labeling sequence data[C]//Anon.Proceedings of the International Conference on Machine Learning,Williamstown,USA:282-289.
[150]Mcdonald R,Pereira F.Online learning of approximate dependency parsing algorithms[C]//Anon.Proceedings of the EACL 2006:81-88.
[151]Berger A,Pietra D S,Pietra D V.A maximum entropy approach to natural language processing [J].Computational Linguistics.1996,22(1):39-71.
[152]Surdeanu M,Johansson R,Meyers A,et al.The CoNLL 2008 Shared Task on Joint Parsing of Syntactic and Semantic Dependencies[C]//Anon.Proceedings of the CoNLL-2008,Manchester,UK:159-177.
[153]Altun Y,Tsochantaridis I,Hofmann T.Hidden Markov Support Vector Machines[C]//Anon.Proceedings of ICML 2003,Washington,DC,USA:172-188.
[154]Tsochantaridis T,Hofmann T,Joachims T,et al.Support Vector Machine Learning for Interdependent and Structured Output Spaces[C]//Anon.Proceedings of ICML 2004,Banff,Canada:823-830.
[155]Preiss J.Using grammatical relations to compare parsers[C]//Anon.Proceedings of the 10th Conference of the European Chapter of the ACL,Budapest,Hungary:291-298.
[156]Merit P,Ferrer E E.The Notion of Argument in Prepositional Phrase Attachment[J].Computational Linguistics.2006,32(3):341-378.
[157]Bethard S,Yu H,Thornton A,et al.Automatic Extraction of Opinion Propositions and their Holders [C]//Anon.Proceedings of AAAI Spring Symposium on Exploring Attitude and Affect in Text:Theories and Applications,Stanford University,USA.
[158]周强.汉语语料库的短语自动划分和标注研究[D].[S.1.]:北京大学,2002.
[159]Kiss T,Strunk J.Unsupervised multilingual sentence boundary detection[J].Computational Linguistics.2002,32(4):485-525.
[160]王小捷,常宝宝.自然语言处理技术基础[M].[S.1.]:北京:北京邮电大学出版社,2002.
[161] Manning C D, Schuetze H. Foundations of statistical natural language processing [M]. [S. 1.]: MIT Press, 1999.
[162] 林杏光.现代汉语动词大词典[M]. [S. 1.]:北京语言学院出版社, 1994.
[163] Taskar B, Guestrin C, Koller D. Max-margin Markov networks [C] // Anon. Advances in Neural Information Processing Systems 16, Cambridge, MA.
[164] Tsochantaridis I, Joachims T, Hofmann T, et al. Large Margin Methods for Structured and Interdependent Output Variables [J]. The Journal of Machine Learning Research. 2005, 6: 1453-1484.
[165] Joachims T. A support vector method for multivariate performance measures [C] // Anon. Proceedings of International Conference on Machine Learning, Bonn, Germany: 377-384.
[166] Tikhonov A N. Solution of incorrectly formulated problems and the regularization method [J].Soviet Math. Dokl. 1963: 1035-1038.
[167] Jurafsky D, Martin J H. Speech and Language Processing: An Introduction to Natural Language Processing, Speech Recognition, and Computational Linguistics [M]. [S. 1.]: Prentice-Hall, 2000.
[168] Durbin R, Eddy S, Krogh A, et al. Biological Sequence Analysis: Probabilistic Models of Proteins and Nucleic Acids [M]. [S. 1.]: Cambridge University Press, 1998.
[169] Dietterich T G. Machine learning for sequential data: A review [C] // Anon. Proceedings of the Joint IAPR International Workshop on Structural, Syntactic, and Statistical Pattern Recognition:15-30.
[170] Rabiner L. A Tutorial on Hidden Markov Models and Selected Applications in Speech Recognition [C] // Anon. Proceedings of the IEEE: 257-286.
[171] Juang B, Rabiner L. Hidden Markov models for speech recognition [J]. Technometrics. 1991, 22:251-272.
[172] Mccallum A, Freitag D, Pereira F. Maximum Entropy Markov Models for Information Extraction and Segmentation [C| // Anon. Proceedings of ICML 2000, Stanford University, USA: 591-598.
[173] Collins M. Ranking algorithms for named-entity extraction: Boosting and the voted perceptron [C]// Anon. Proceedings of the 40nd ACL, Philadelphia, Pennsylvania, USA: 489-496.
[174] Collins M, Roark B. Incremental parsing with the perceptron algorithm [C] // Anon. Proceedings of the 42nd ACL.
[1751 Jordan M I. Serial order: A parallel distributed processing approach [R]. [S. 1.]: [s. n.]. 1987.
[176] Lafferty J, Zhu X, Liu Y. Kernel conditional random fields: representation and clique selection [C]// Anon. Proceedings of the International Conference on Machine Learning.
[177]Nguyen N,Guo Y.Comparisonsof sequence labeling algorithms and extensions[C]//Anon.Proceedings of ICML 2007,Corvalis,Oregon:681-688.
[178]Ratsch G,Sonnenburg S.Large scale hidden semi-Markov SVMs[C]//Anon.Proceedings of the Advances in Neural Information Processing Systems.
[179]Vapnik V.Statistical Learning Theory[M].[S.1.]:Wiley,1998.
[180]Bottou L,Cortes C,Denker J,et al.Comparison of classifier methods:A case study in handwriting digit recognition[C]//Anon.Proceedings of International Conference on Pattern Recognition,Jerusalem,Israel:77-87.
[181]Kressel U.Pairwise classification and support vector machines[J].Advances in Kernel Methods-Support Vector Learning.1999.
[182]Weston J,Watkins C.Multi-class support vector machines[R].[S.1.]:[s.n.],1998.
[183]Crammer K,Singer Y.On the algorithmic implementation of multiclass kernel-based vector machines [J].Journal of Machine Learning Research.2001:265-292.
[184]Schwarz R,Chow Y L.The n-best algorithm:An efficient and exact procedure for finding the N most likely hypotheses[C]//Anon.Proceedings of the IEEE International Conference on Acoustics,Speech and Signal Processing:81-84.
[185]Taskar B,Guestrin C,Koller D.Max Margin markov networks[C]//Anon.Proceedings of Advances in neural information processing systems.
[186]Platt J C.Using analytic QP and sparseness to speed training of support vector machines[C]//Anon.Proceedings of Advances in neural information processing systems:557563.
[187]Xue N.Labeling Chinese Predicates with Semantic Roles[J].Computational Linguistics.2005,34(2):225-255.
[188]Che W,Zhang M,Liu T,et al.A Hybrid Convolution Tree Kernel for Semantic Role Labeling[C]//Anon.Proceedings of the 21st International Conference on Computational Linguistics and the 44th ACL,Sydney,Australia:73-80.
[189]朱德熙.语法讲义[M].[S.1.]:商务印书馆,1982.
[190]张华平,刘群.基于N-最短路径方法的中文词语粗分模型[J].中文信息学报.2002,16(5):77-84.
[191]Gao J,Li M,Huang C-N.Improved source-channel models for Chinese word segmentation[C]//Anon.Proceedings of the 41st ACL,Sapporo,Japan:7-12.
[192]刘群,张华平,俞鸿魁,et al.基于层叠隐马模型的汉语词法分析[J].计算机研究与发展.2004,41(8):1421-1429.
[193]张亮,黄河燕,胡春玲.基于Multigram语言模型的主动学习中文分词[J].中文信息学报.2006,20(1):50-58.
[194]Zhang H,Yu H,Xiong D,et al.HHMM-based Chinese Lexical Analyzer ICTCLAS[C]//Anon.Proceedings of Second SIGHAN workshop affiliated with 41th ACL,Sapporo,Japan:184-187.
[195]Qin Y,Yuan C,Sun J,et al.BUPT Systems in the SIGHAN Bakeoff 2007[C]//Anon.Proceedings of the Sixth SIGHAN Workshop on Chinese Language Processing,Hyderabad,India:94-97.
[196]陈小荷.现代汉语自动分析[M].[S.1.]:北京:北京语言文化大学出版社,2000.
[197]Gao J,Wu A,Li M,et al.Adaptive Chinese Word Segmentation[C]//Anon.Proceedings of the 42nd ACL,Barcelona,Spain:311-318.
[198]屈刚,陆汝占.一个改进的汉语词性标注系统[J].上海交通大学学报.2003,37(6):897-900.
[199]张孝飞,陈肇雄,黄河燕,et al.词性标注中生词处理算法研究[J].中文信息学报.2003,17(5):1-5.
[200]Yuan C,Wang X,Zhong Y.Some improvements on maximum entropy based Chinese POS tagging [J].THEJOURNAL OF CHINA UNIVERSITIES OF POSTS AND TELECOMMUNICATIONS.2004,13(13):14-18.
[201]Wang M,Sagae K,Mitamura T.A Fast,Accurate Deterministic Parser for Chinese[C]//Anon.Proceedings of the the 44th ACL,Sydney,Australia:425-432.
[202]Forman G.An extensive empirical study of feature selection metrics for text classification[J].Journal of Machine Learning Research:Special Issue on Variable and Feature Selection.2003:1289-1305.
[203]Wiebe J M,Wilson T,Bruce R F,et al.Learning subjective language[J].ComputationalLinguistics.2004,30(3):277-308.
[204]Gamon M,Aue A.Development and use of a gold standard data set for subjectivity classifications [C]//Anon.Proceedings of Workshop on Sentiment and Subjectivity in Text of COLING/ACL 2006.
[205]Turney P D.Thumbs up or thumbs down? Semantic orientation applied to unsupervised classification of reviews[C]//Anon.Proceedings of the 40th ACL,Philadelphia,Pennsylvania:417-424.
[206]Hu M,Liu B.Mining and summarizing customer reviews[C]//Anon.Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery & Data Mining(KDD-2004),Seattle,WA,USA:168-177.
[207]Ku L-W,Chen H-H.Mining Opinions from the Web:Beyond Relevance Retrieval[J].Journal of American Society for Information Science and Technology,Special Issue on Mining Web Resources for Enhancing Information Retrieval.2000,58(12):1838-1850.
[208]董静,王万森.E-learning系统中情感识别的研究[J].计算机工程与设计.2008,29(17):4525-4534.
[209]T Wilson J W,Hoffmann P.Recognizing contextual polarity in phrase-level sentiment analysis[C]//Anon.Proceedings of the HLT/EMNLP 2005.
[210]Kim S-M,Eduard H.Identifying Opinion Holders for Question Answering in Opinion Texts[C]//Anon.Proceedings of AAAI-05 Workshop on Question Answering in Restricted Domains,Pittsburgh,USA.
[211]Pang B,Lee L,Vaithyanathan S.Thumbs up? Sentiment Classification using Machine Learning Techniques[C]//Anon.Proceedings of EMNLP 2002,San Jose,CA,USA:79-86.
[212]Somasundaran S,Wiebe J,Ruppenhofer J.Discourse Level Opinion Interpretation[C]//Anon.Proceedings of the 22nd International Conference on Computational Linguistics(COLING-2008),Manchester,UK.
[213]Choi Y,Cardie C,Riloff E,et al.Identifying sources of opinions with conditional random fields and extraction patterns[C]//Anon.Proceedings of the HLT/EMNLP 2005.
[214]Seki Y,Evans D K,Ku L-W,et al.Overview of Opinion Analysis Pilot Task at NTCIR-6[C]//Anon.Proceedings of NTCIR-6 Workshop Meeting,Tokyo,Japan:265-278.
[215]Xu R,Wong K-F,Xia Y.Opinmine-Opinion Analysis System by CUHK for NTCIR-6 Pilot Task [C]//Anon.Proceedings of NTCIR-6 Workshop Meeting,Tokyo,Japan:350-357.
[216]Li Y,Bontcheva K,Cunningham H.Experiments of Opinion Analysis on the Corpora MPQA and NTCIR-6[C]//Anon.Proceedings of NTCIR-6 Workshop Meeting,Tokyo,Japan:323-329.
[217]Huang R,Sun L,Pan L.ISCAS in Opinion Analysis Pilot Task:Experiments with sentimental dictionary based classifier and CRF model[C]//Anon.Proceedings of NTCIR-6 Workshop Meeting,Tokyo,Japan:296-300.
[218]Ku L-W,Lo Y-S,Chen H-H.Using Opinion Scores of Words for Sentence-Level Opinion Extraction [C]//Anon.Proceedings of NTCIR-6 Workshop Meeting,Tokyo,Japan:316-322.
[219]Wu Y,Oard D.NTCIR-6 at Maryland:Chinese Opinion Analysis Pilot Task[C]//Anon.Proceedings of NTCIR-6 Workshop Meeting,Tokyo,Japan:344-349.
[220]Stoyanov V,Cardie C.Annotating Topics of Opinions[C]//Anon.Proceedings of the Sixth International Language Resources and Evaluation(LREC'08),Marrakech,Morocco.
[221]史树敏,黄河燕,刘东升.自然语言文本共指消解性能评测算法研究[J].计算机科学.2008,35(9):168-177.
[222]Xue N.Annotation Guidelines for the Penn Chinese Proposition Bank(1st Draft)[R].[S.1.]:[s.n.],2007.
[223]Yuan C,Wang X,Zhong Y.Some Improvements on Maximum Entropy based Chinese POS Tagging [J].The Journal of China Universities of Posts and Telecommunications.2006:99-103.
[224]Yuan C,Wang X,Ren F,et al.Function Labeling for Unparsed Chinese Text[J].IEEJ Transactions on Electronics,Information and Systems,Section C,Japan.2009.(Accepted).
[225]Yuan C,Ren F.Accurate Learning for Chinese Function Tags from Lexical Evidence[J].Chinese Journal of Electronics.2009.(Accepted).
[226]Yuan C,Ren F,Wang X.Accuracy Learning for Chinese Function Tags from Minimal Features [C]//Anon.Proceedings of the ACL-IJCNLP 2009 Student Research Workshop.
[227]Yuan C,Wang X,Ren F,et al.Exploiting Lexical Information for Function Tag Labeling[C]//Anon.Proceedings of the IEEE NLP-KE'08,Beijing,China:67-74.
[228]Qin Y,Yuan C,Sun J.et al.BUPT Systems in the SIGHAN Bakeoff 2007[C]//Anon.Proceedings of the Sixth SIGHAN Workshop on Chinese Language Processing,Hyderabad,India:94-97.
[229]Cai J,Yuan C,Wang X,et al.Semantic Role Labeling for Multi-VP Clauses in Chinese[C]//Anon.Proceedings of the IEEE NLP-KE'07,Beijing,China:367-372.
[230]Yuan C,Wang C.Parsing Model for Answer Extraction in Chinese Question Answering System [C]//Anon.Proceedings of the IEEE NLP-KE'05,Wuhan,China:206-211.
[231]Yuan C.Wang J,Wang C.The Web-based Domain Independent DM for Intelligent Spoken Dialog System[C]//Anon.Proceedings of the IEEE Networking,Sensing and Control Proceedings,Arizona,USA:1027-1030.
[232]Yuan C,Yu L,Sun X,et al.Assigning Function Tags to Unparsed Text[C]//Anon.2008 International Symposium on Artificial and Affective Computing/AIAC-08),Tokushima.Japan:189-200.
[233]Yuan C,Ren F.Predicate-Argument Annotating for Unparsed Text[C]//Anon.2008 Shikokusection Joint Convention of the Institutes of Electrical and related Engineers.Tokushima,Japan.
[234]Yuan C,Wang X.Semi-supervised Maximum Entropy Based POS Tagging for Large Scale Chinese Corpus[C]//Anon.Proceedings of the 3rd Students' Workshop on Computational Linguistics,Shenyang,China:99-104.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |