面向查询的多文档自动文摘关键技术研究
|
摘要
随着互联网的迅速发展和文本信息的日益增多,从大量信息中快速查找和获取有用信息的迫切需求使得自动文摘技术日益重要。自动文摘是指由计算机自动从一篇或多篇文本中概括出主要内容,从而把大量原来需要用户来完成的工作都交给计算机自动完成,节省了用户浏览信息的时间,减轻了用户负担。这个任务涉及到文本理解、文本生成等自然语言处理领域的多个方面,对于计算机具有很大的挑战性。本文正是在这种前提下,对自动文摘技术进行了探索性研究。
本文在面向查询的多文档自动文摘方面以及文摘连贯性的自动评价方面做了深入的研究工作。我们在这两年参加文摘方面的国际评测会议DUC的基础上,研究并实现了多种面向查询的多文档自动文摘技术。
我们采用了最大熵模型来实现基于机器学习的自动文摘系统。为了进一步找出文档句之间以及句子与查询之间的语义关联,我们提出了一种在文摘系统中进行语义扩展的方法,该方法通过WordNet中定义的同义词集以及词与词之间的语义关系,对传统的基于词的句子向量进行语义扩展,从而将语义信息融入到句子中,使得系统性能比起语义扩展前得到了显著提高。
本文还提出了一种基于图排序算法的查询扩展方法,将其结合到面向查询的自动文摘系统中,可以很好的解决原始查询中通常包含信息量不足的问题。该扩展方法在句一句关系以及句一词关系的基础上利用上下文信息对查询进行扩展,能够以较少的噪声获取到更多相关信息。加入了查询扩展后的文摘系统在性能上比扩展前有明显的提高,在DUC标准评测语料上达到了目前的最好结果,充分表明了该查询扩展方法的有效性。
自动文摘研究的另一个主要方面是文摘的评测。当前对文摘的自动评测主要在于考察文摘的内容覆盖率,对文摘语言质量如可读性、连贯性等方面的评测则由人工完成,由于需要消耗大量人力而且缺乏客观性,使得人工评测方法不能普及,所以如何能对文摘的语言质量进行自动评测是一个重要研究问题。本文提出了一种对文摘连贯性的自动评价模型。在文摘连贯性的自动评价上,我们对基于实体的连贯性基本模型从特征和实体选取等方面做了深入研究,通过考虑网格中的邻居以及非相邻句等信息对原有实体转移特征进行了细化;分析了实体选择在模型中的重要性,并且通过潜在语义分析重新建立了实体网格,从而对原有模型进行了改进,在实验中获得了更高的准确率。
With the quick development of Internet and increasing amount of text information, the requirement of searching from large amount of texts to get useful information has made automatic summarization more and more important. Automatic summarization means summarizing from single or multiple documents to get generalized content automatically. It can save much time for the users when browsing. This task is related to multiple aspects in the area of natural language processing, which is a big challenge for the computer. We described our research work on the technique of automatic summarization in this thesis.
We have done much work on query-focused multi-document summarization and automatic evaluation of summary coherence. We have realized several summarization systems on the basis of participation in the DUC evaluation in recent years.
We use CME model for machine learning based automatic summarizer. Furthermore, in order to find the semantic relatedness between sentences and the queries, we proposed a method of semantic extension which is applied to the summarization system. In this method, sentence vectors can be semantically extended based on the Synset and different word relations defined in WordNet. In this way, semantic information can be combined into the sentences and the performance of the summarization system gets obvious improvement.
We also proposed a method of query expansion based on graph-based ranking algorithm, which is combined into the query-focused summarization system to solve the problem of information paucity in the original query. This method makes use of context information to expand the query, which can obtain more relevant information with less noise. The summarization system with query expansion has obtained significant performance improvement compared to without expansion, and we have achieved the state-of-the-art performance on the evaluation data from DUC.
Another important problem is the summary evaluation. Currently the evaluation on linguistic quality relies on manual evaluation, which is time-consuming, so it is important to develop automatic method. We have studied the entity-based coherence model and improved it from both feature calculation and entity selection. In both ways we have improved the base model and got higher accuracy in the experiments.
本文在面向查询的多文档自动文摘方面以及文摘连贯性的自动评价方面做了深入的研究工作。我们在这两年参加文摘方面的国际评测会议DUC的基础上,研究并实现了多种面向查询的多文档自动文摘技术。
我们采用了最大熵模型来实现基于机器学习的自动文摘系统。为了进一步找出文档句之间以及句子与查询之间的语义关联,我们提出了一种在文摘系统中进行语义扩展的方法,该方法通过WordNet中定义的同义词集以及词与词之间的语义关系,对传统的基于词的句子向量进行语义扩展,从而将语义信息融入到句子中,使得系统性能比起语义扩展前得到了显著提高。
本文还提出了一种基于图排序算法的查询扩展方法,将其结合到面向查询的自动文摘系统中,可以很好的解决原始查询中通常包含信息量不足的问题。该扩展方法在句一句关系以及句一词关系的基础上利用上下文信息对查询进行扩展,能够以较少的噪声获取到更多相关信息。加入了查询扩展后的文摘系统在性能上比扩展前有明显的提高,在DUC标准评测语料上达到了目前的最好结果,充分表明了该查询扩展方法的有效性。
自动文摘研究的另一个主要方面是文摘的评测。当前对文摘的自动评测主要在于考察文摘的内容覆盖率,对文摘语言质量如可读性、连贯性等方面的评测则由人工完成,由于需要消耗大量人力而且缺乏客观性,使得人工评测方法不能普及,所以如何能对文摘的语言质量进行自动评测是一个重要研究问题。本文提出了一种对文摘连贯性的自动评价模型。在文摘连贯性的自动评价上,我们对基于实体的连贯性基本模型从特征和实体选取等方面做了深入研究,通过考虑网格中的邻居以及非相邻句等信息对原有实体转移特征进行了细化;分析了实体选择在模型中的重要性,并且通过潜在语义分析重新建立了实体网格,从而对原有模型进行了改进,在实验中获得了更高的准确率。
With the quick development of Internet and increasing amount of text information, the requirement of searching from large amount of texts to get useful information has made automatic summarization more and more important. Automatic summarization means summarizing from single or multiple documents to get generalized content automatically. It can save much time for the users when browsing. This task is related to multiple aspects in the area of natural language processing, which is a big challenge for the computer. We described our research work on the technique of automatic summarization in this thesis.
We have done much work on query-focused multi-document summarization and automatic evaluation of summary coherence. We have realized several summarization systems on the basis of participation in the DUC evaluation in recent years.
We use CME model for machine learning based automatic summarizer. Furthermore, in order to find the semantic relatedness between sentences and the queries, we proposed a method of semantic extension which is applied to the summarization system. In this method, sentence vectors can be semantically extended based on the Synset and different word relations defined in WordNet. In this way, semantic information can be combined into the sentences and the performance of the summarization system gets obvious improvement.
We also proposed a method of query expansion based on graph-based ranking algorithm, which is combined into the query-focused summarization system to solve the problem of information paucity in the original query. This method makes use of context information to expand the query, which can obtain more relevant information with less noise. The summarization system with query expansion has obtained significant performance improvement compared to without expansion, and we have achieved the state-of-the-art performance on the evaluation data from DUC.
Another important problem is the summary evaluation. Currently the evaluation on linguistic quality relies on manual evaluation, which is time-consuming, so it is important to develop automatic method. We have studied the entity-based coherence model and improved it from both feature calculation and entity selection. In both ways we have improved the base model and got higher accuracy in the experiments.
引文
[Alemany and Fuentes 2003]Alemany L.A.and Fuentes Fort M.Integrating cohesion and coherence for automatic summarization[C].In Proceedings of the Tenth Meeting of the European Chapter of the Association for Computational Linguistics(EACL '03).2003.
[Barzilay and Elhadad 1997]Barzilay R.and Elhadad M.Using Lexical Chains for Text Summarization[C].In ACL/EACL-97 summarization workshop.Madrid,1997.
[Barzilay et al.2002]Barzilay R.,Elhadad N.,and McKeown K.R.Inferring Strategies for Sentence Ordering in Multidocument News summarization[J].Journal of Artificial Intelligence Research,volume 17,pages 35-55.2002.
[Barzilay and Lapata 2005]Barzilay R.and Lapata M.Modeling local coherence:An entity-based approach[C].In Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics(ACL'05).2005.
[Barzilay and Lapata 2007]Barzilay R.and Lapata M.Modeling local coherence:An entity-based approach[J].Computational Linguistics.To appear.2007.
[Barzilay and Lee 2004]Barzilay R.and Lee L.Catching the drift:Probabilistic content models,with applications to generation and summarization[C].In Proc.of the HLT-NAACL 2004:Proceedings of the Main Conference,(pp.113-120).2004.
[Barzilay and Mckeown 2005]Barzilay R.and Mckeown K.R.Sentence Fusion for Multidocument News Summarization[J].Computational Linguistics 31(3):297-328.2005.
[Baxendale 1958]Baxendale P.E.Machine-made index for technical literature-an experiment[J].IBM Journal of Research and Development,Vol.2,No.4.1958.
[Berger et al.1996]Berger,A.L.,Della Pietra,S.A.,and Della Pietra,V.J.A maximum entropy approach to natural language processing[J].Computational Lingustics,22(1),38-73.1996.
[Bollegala et al.2005a]Bollegala D.,Okazaki N.,and Ishizuka M.A Machine Learning Approach to Sentence Ordering for Multidocument Summarization and Its Evaluation[C].In Proceedings of International Joint Conference on Natural Language Processing 2005.pp.624-635.
[Bollegala et al.2005b]Bollegala D.,Okazaki N.,and Ishizuka M.A Clustering Based Approach to Sentence Ordering for Multidocument Summarization and its Evaluation[C].In Proceedingss of the 19th Annual Conference of the Japanese Society for Artificial Intelligence,2005.
[Bollegala et al.2006]Bollegala D.,Okazaki N,and Ishizuka M.A Bottom-up approach to sentence ordering for multi-document summarization[C].In Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the ACL,(pp.385-392).Sydney,Australia.2006.
[Budanitsky 1999]Budanitsky A.Lexical semantic relatedness and its application in natural language processing[R].Technical Report CSRG-390,University of Toronto,August 1999.
[Budanitsky and Hirst 2001]Budanitsky A.and Hirst G.Semantic distance in Word.Net:An experimental,application-oriented evaluation of five measures[C].In Proceedings of NAACL Workshop on WordNet and other lexical resources,pp.29-34.2001.
[Carbonell and Goldstein 1998]Carbonell,J.and Goidstein,J.The use of MMR,diversity-based reranking for reordering documents and producing summaries[C].In Proceedings of SIGIR 1998(pp.335-336).Melbourne,Australia.1998.
[Cohen et al.1999]Cohen William W.,Schapire Robert E.,and Singer Y.Learning to Order Things[J].Journal of Artificial Intelligence Research,1999.
[Collins 1997]Collins M.Three generative,lexicalised models for statistical parsing[C].In Proceedings of the ACL/EACL,16-23.1997.
[Conroy and Leary 2001]Conroy J.M.and Leary D.P.Text Summarization via Hidden Markov Models and Pivoted QR Matrix Decomposition[R].Technical report,University of Maryland,College Park,Maryland,March,2001.
[Conroy and Schlesinger 2005]Conroy J.M.and Schlesinger J.D.CLASSY query-based multi-document summarization[C].In Proceedings of DUC 2005.
[Dang 2005]Dang H.T..Overview of DUC 2005[C].In Proceedings of Document Understanding Conference 2005.
[Dang 2006]Dang H.T.Overview of DUC 2006[C].In Proceedings of Document Understanding Conference 2006.
[Daume and Marcu 2005a]Daume H.and Marcu D.Bayesian Summarization at DUC and a Suggestion for Extrinsic Evaluation[C].In Proceedings of Document Understanding Conference,2005.
[Daume and Marcu 2005b]Daume H.and Marcu D.Bayesian Multi-Document Summarization at MSE[C].In ACL 2005 Workshop on Intrinsic and Extrinsic Evaluation Measures.2005.
[Daume and Marcu 2006]Daume H.and Marcu D.Bayesian Query-Focused Summarization[C].In Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the ACL,pages 305-312.Sydney,July 2006.
[DUC]Document Understanding Conference.http://duc.nist.gov.
[Edmundson et al.1959]Edmundson H.P.,Oswald V.A.,and Wyllys R.E.Automatic Indexing and Abstracting of Contents of Documents[J].Planning Research Corporation,Los Angeles,California.1959.
[Eisner et al.2007]Eisner M,Austerweil J.,and Charniak E.A unified local and global model for discourse coherence[C].In proc.of NAACL 2007.
[Erkan and Radev 2004a]Erkan G.and Radev D.R.LexRank:Graph-based lexical centrality as salience in text summarization[J].Journal of Artificial Intelligence Research,22:457-479.2004.
[Erkan and Radev 2004b]Erkan G.and Radev D.R.LexPageRank:Prestige in Multi-Document Text Summarization[C].In Proceedings of EMNLP 2004.Barcelona,Spain.
[Erkan 2006]Erkan G.Using Biased Random Walks for Focused Summarization[CJ.In Proceedings of DUC 2006.
[Farzindar et al.2005]Farzindar A.,Rozon F.,and Lapalme G.CATS a topic-oriented multi-document summarization system at DUC 2005[C].In Proceedings of Document Understanding Conference 2005.
[Fellbaum 1998]Fellbaum C.WordNet:An electronic lexical database[M].MIT Press,1998
[Foltz et al.1998]Foltz P.W.,Kintsch W.,and Landauer T.K.Textual coherence using latent semantic analysis[J].Discourse Processes,25(2&3),285-307.1998.
[George et al.1993]George A.Miller,Richard Beckwith,Christiane Fellbaum.Introduction to WordNet:An On-line Lexical Database[J].International Journal of Lexicography,3:235-3121993.
[Goldensohn 2005]Goldensohn S.B.Columbia University at DUC 2005[C].In Proceedings of Document Understanding Conference 2005.
[Gong and Liu 2001]Gong Y.and Liu X.Generic Text Summarization Using Relevancce Measure and Latent Semantic Analysis[C].In Proceedings of SIGIR 2001.New Orleans,USA.2001.
[Good 1963]Good I.J.Maximum Entropy for Hypothesis Formulation,especially for Multidimensional Contingency Tables[J].In The Annals of Mathematical Statistics,34(3):911-934,1963
[Grosz et al.1995]Grosz,B.J.,Joshi,A.K.,and Weinstein,S.Centering:A framework for modeling the local coherence of discourse[J].Computational Linguistics,21(2):203-225.1995.
[Haveliwala 2002]Haveliwala T.H.Topic-Sensitive PageRank[C].In Proc.of WWW2002,May 7-11,2002,Honolulu,Hawaii,USA.
[Hirst and St-Onge 1998]Hirst G.and St-Onge D.Lexical chains as representations of context for the detection and correction of malapropisms[J].In Fellbaum 1998,pp.305-332.
[Hotho et al.2003]Hotho A.,Staab S.,and Stumme G.WordNet improves text document clustering[C].In Proc.of the SIGIR 2003 Semantic Web Workshop,2003.
[Hovy et al.2005]Hovy E.,Lin C-Y,and Zhou L.Evaluating DUC 2005 using Basic Elements [C].In Proc.of Document Understanding Conference 2005.
[Jiang and Conrath 1997]Jiang Jay J.and Conrath David W.Semantic similarity based on corpus statistics and lexical taxonomy[C].In Proceedings of International Conference on Research in Computational Linguistics,Taiwan.
[Joachims 2002]Joachims T.Optimizing search engines using clickthrough data[C].In Proceesings of KDD,133-142.2002.
[Kibble and Power 2004]Kibble R.and Power R.Optimising referential coherence in text generation[J].Computational Linguistics,30(4):401-416.2004.
[Kieinberg 1999]Kleinberg J.M.Authoritative sources in a hyperlinked environment[J].Journal of the ACM,46(5):604-632,1999.
[Knight and Marcu 2000]Knight K.and Marcu D.Statistics-Based Summarization-Step One:Sentence Compression[C].In Proceedings of AAAI 2000.
[Kupiec et al.1995]Kupiec J.,Pedersen J.,and Chen F.A Trainable Document Summarizer[C].In Proceedings of the Eighteenth Annual International ACM Conference on Research and Development in Information Retrieval(SIGIR),68-73.Seattle,WA.1995.
[Lacatusu et al 2005]Lacatusu F.,Hickl A.,Aarseth P.,and Taylor L.Lite-GISTexter at DUC 2005[C].In Proc.of DUC 2005.
[Lafferty and Zhai 2001]Lafferty J.and Zhai C.Document language models,query models,and risk minimization for information retrieval[C].In Proceedings of the Conference on Research and Developments in Information Retrieval(SIGIR).2001.
[Landauer and Dumais 1997]Landauer T.K.and Dumais S.T.A solution to Plato's problem:The latent semantic analysis theory of acquisition,induction and representation of knowledge [J].Psychological Review,104(2):211-240.1997.
[Lapata 2003]Lapata M.Probabilistic text structuring:Experiments with sentence ordering[C].In Proceedings of the 41st Annual Meeting of the Association for Computational Linguistics,(pp.545-552).Sapporo,Japan.2003.
[Lapata and Barzilay 2005]Lapata M.and Barzilay R.Automatic evaluation of text coherence:Models and representations[C].In Proc.of the 19th International Joint Conference on Artificial Intelligence(IJCAI-05),(pp.1085-1090).2005.
[Lavrenko et al.2002]Lavrenko V.,Choquette M.,and Croft B.Crosslingual re&vance models [C].In Proceedings of the Conference on Research and Developments in Information Retrieval(SIGIR).2002.
[Leacock and Chodorow 1998]Leacock C.and Chodorow M.Combining local context and WordNet similarity for word sense identification[J].In Fellbaum 1998,pp.265-283.
[Li et al.2005]Li W.,Li W.,Li B.,Chen Q.,and Wu M.The Hong Kong Polytechnic University at DUC2005[C].In Proceedings of Document Understanding Conference 2005.
[Lin 1998]Lin D.An information-theoretic definition of similarity[C].In Proceedings of the 15th International Conference on Machine Learning,Madison,WI.1998.
[Lin 2001]Lin C.Y,Summary Evaluation Environment.http://www.isi.edu/～cyl/SEE.
[Lin 2004]Lin C.Y.ROUGE:A Package for Automatic Evaluation of Summaries[C].In Proceedings of Workshop on Text Summarization Branches Out,Post-conference Workshop of ACL 2004,Barcelona,Spain.2004.
[Lin and Hovy 2003]Lin C.Y.and Hovy E.Automatic evaluation of summaries using n-gram co-occurrence[C].In Proceedings of HLT-NAACL 2003.Edmonton,Canada.2003.
[Liu et al.2004]Liu Y.,et al.Affinity Rank." A New Scheme for Efficient Web Search[C].In Proceedings of WWW 2004,May 17-22,2004,New York,USA.
[Luhn 1958]Luhn H.P.The automatic creation of literature abstract[J].IBM Journal of Research and Development.1958,2(2):159-165.
[Mani et al.1998]Mani I.,Bloedom E.,and Gates B.Using cohesion and coherence models for text summarization[C].In Proceedings of AAAI Spring Symposium on Intelligent Text Summarization,Stanford(pp.69-76).1998.
[Mani 2001]Mani J.Automatic Summarization[M].Amsterdam/Philadephia:John Benjamins Publishing Company.2001.
[Mann and Thompson 1988]Mann,W.C.& Thompson,S.A.Rhetorical structure theory:Toward a functional theory of text organization[J].Text,8,3,243-281.1988.
[Marcu 1997]Marcu D.From local to global coherence:A bottom-up approach to text planning [C].In Proceedings of the 14th National Conference on Artificial Intelligence,(pp.629-635).Providence,Rhode Island.1997.
[Mckeown et al.1999]Mckeown K.,Klavans J.,Hatzivassiloglou V.,Barzilay R.,and Eskin E.Towards Multidocument Summarization by Reformulation:Progress and Prospects[C].In Proceedings of AAAI 1999.
[Mihalcea and Tarau 2004]Mihalcea,R.and Tarau,P.TextRank:Bringing order into texts[C].In Proceedings of EMNLP 2004(pp.404-411).Barcelona,Spain.
[Miller et al.1993]Miller G.,Beekwith R.,Fellbaum C.,Gross D.,and Miller K.J.Five Papers on WordNet[R].Technical Report,Princeton University,1993.
[Miltsakaki and Kukichy 2000]Miltsakaki E.and Kukichy K.Automated evaluation of coherence in student essays[C].In Proceedings of the Workshop on Language Resources and Tools in Educational Applications,Athens(pp.7-14).2000.
[Molina 1995]Molina P.Document abstracting:Toward a methodological model[J].Journal of the American Society for Information Science 46(3).1995.
[Morris et al.1992]Morals A,Kasper G,and Adams D.The Effects and Limitations of Automatic Text Condensation on Reading Comprehension Performance[J].Information Systems Research, 26:17-35.1992.
[Motwani and Raghavan 1995] Motwani R. and Raghavan P. Randomized Algorithms [MJ. Cambridge University Press, United Kingdom, 1995.
[Nenkova and Passonneau 2004] Nenkova A. and Passonneau R. Evaluating Content Selection in Summarization: The Pyramid Method [C]. In Proc. of NAACL-HLT 2004.
[Ng and Cardie 2002] Ng V. and Cardie C. Improving machine learning approaches to coreference resolution [CJ. In Proceedings of the ACL, 104-111.2002.
[Nie et al. 2006] Nie L., Davison B. D., and Qi X. Topical Link Analysis for Web Search [C]. In Proceedings of SIGIR'06, August 6-11,2006, Seattle, Washington, USA.
[Okazaki et al. 2004] Okazaki N, Matsuo Y., and Ishizuka M. Improving chronological sentence ordering by precedence relation [C]. In Proceedings of 20th International Conference on Computational Linguistics (COLING 04), (pp. 750-756). 2004.
[Otterbacher et al. 2005] Otterbacher J., Erkan G., and Radev D. R. Using random walks for question-focused sentence retrieval [CJ. In Proc. of HLT-EMNLP 2005. Vancouver, BC.
[Page et al. 1998] Page L., Brin S., Rajeev M., and Terry W. The PageRank citation ranking: Bringing order to the web [RJ. Technical report, Stanford University, Stanford, CA. 1998.
[Papineni et al. 2001] Papineni, K., S. Roukos, T. Ward, and Zhu W. J. BLEU: a Method for Automatic Summarization of Machine Translation [RJ. IBM Research Report RC22176(W0109-022). 2001.
[Pietra et al. 1997] Pietra S. D., Pietra V. D., Lafferty J. Inducing Features of Random Fields [J]. In IEEE Transactions on Pattern Analysis and Machine Intelligence, 19(4): 380-393,1997.
[Ponte and Croft 1998] Ponte J. M. and Croft B. A language modeling approach to information retrieval [CJ. In Proceedings of the Conference on Research and Developments in Information Retrieval (SIGIR). 1998.
[Radev et al. 2000] Radev D. R., Jing H., and Budzikowska M. Summarization of multiple documents: clustering, sentence extraction, and evaluation [CJ. In Proceedings of ANLP-NAACL Workshop on Automatic Summarization, 21-30. Seattle, WA, 2000.
[Radev et al. 2004] Radev, D. R., Jing, H. Y., Stys, M., and Tam, D. Centroid-based summarization of multiple documents [J]. Information Processing and Management, 40, 919-938. 2004.
[Rau et al.1989]Rau L.F.,Jacobs P.S.,and Zemik U.Information Extraction and Text Summarization Using Linguistic Knowledge Acquisition[J].Information Processing and Management.Vol.25,No.4.1989.
[Resnik 1995]Resnik P.Using information content to evaluate semantic similarity[C].In Proceedings of the 14th International Joint Conference on Artificial Intelligence,pages 448-453,Montreal.
[Richardson and Domingos 2002]Richardson M.and Domingos P.The Intelligent Surfer:Probabilistic Combination of Link and Content Information in PageRank[C].In Proceedings of NIPS 2002.
[Rush et al.1971]Rush J.E.,Salvador R.,and Zamora A.Automatic abstracting and indexing.Ⅱ:Production of indicative abstracts by application of contextual inference and syntactic coherence criteria[J].Journal of the American Society for Information Science,Vol;.22,No.4.
[Salton and McGill 1983]Salton G.and McGill M.J.Introduction to Modern Information Retrieval[M].New York:McGraw-Hill.1983.
[Seco et al.2004]Seco N.,Veale T.,and Hayes J.An intrinsic information content metric for semantic similarity in WordNet[C].In Proceedings of the 16th European Conference on Artificial Intelligence.Valencia,Spain.2004.
[Soricut and Marcu 2006]Soricut R.and Marcu D.Discourse generation using utility-trained coherence models[C].In Proceedings of the Association for Computational Linguistics Conference(ACL-2006).
[Soubbotin and Soubbotin 2005]Soubbotin M.and Soubbotin S.Trade-Off between Factors Influencing Quality of the Summary[C].In Proceedings of Document Understanding Conference 2005.
[Spark and Galliers 1996]Spark J.K.and Galliers J R.Evaluating Natural Language Processing:An Analysis and Review[M].New York:Springer.1996.
[Teufel and Moens 1997]Teufel S.and Moens M.Sentence Extraction as a Classification Task [C].In Proceedings of the Workshop on Intelligent Scalable Summarization.ACL/EACL Conference,58-65.Madrid,Spain.1997.
[Vandeghinste and Pan 2004]Vandeghinste V.and Pan Y.Sentence Compression for Automated Subtitling:A Hybrid Approach[C].In Proceedings of ACL 2004.
[Wan et al.2007a]Wan X.,Yang J.,and Xiao J.CollabSum:Exploiting Multiple Document Clustering for Collaborative Single Document Summarizations[C].In Proceedings of SIGIR'07,July 23-27,2007,Amsterdam,The Netherlands.
[Wan et al.2007b]Wan X.,Yang J.,and Xiao J.Towards an iterative reinforcement approach for simultaneous document summarization and keyword extraction[C].In Proceedings of ACL 2007(pp.552-559).2007.
[Wan et al.2007c]Wan X.,Yang J,and Xiao J.Manifold-ranking based topic-focused multi-document summarization[C].In Proceedings of IJCAI 2007(pp.2903-2908).2007.
[Zhang et al.2005]Zhang Benyu.et al.Improving web search results using affinity graph[C].In Proceedings of SIGIR 2005.Salvador,Brazil.
[Zhou et ai.2005]Zhou L,Lin C-Y,and Hovy E.A BE-based multi-document summarizer with query interpretation[C].In Proc.of DUC 2005.
[陈2005]陈宁昱 周雅倩 黄萱菁 吴立德.利用未标注语料改进实体名识别性能[J].中文信息学报.Vol 19.No 2.2005:7-11.
[郭2002]郭燕慧 钟义信 马志勇 姚均勇.自动文摘综述[J].情报学报.21(5).2002.
[李2000]李蕾 郭祥昊 钟义信.面向特定领域的理解型中文自动文摘系统[J].计算机研究与发展,37(4):6-10.2000.
[刘1995]刘挺 吴岩 王开铸.基于信息抽取和文本生成的自动文摘系统设计[J].情报学报.16(增刊).1995.
[王1997]王永成 徐慧.OA中文文献自动摘要系统[J].情报学报.16(2).1997.
[吴1997]吴立德等.大规模中文文本处理[M].上海:复旦大学出版社.1997.
[姚1995]姚天顺等.自然语言理解--一种让机器懂得人类语言的研究[M].清华大学出版社,广西科学技术出版社.1995.
[Barzilay and Elhadad 1997]Barzilay R.and Elhadad M.Using Lexical Chains for Text Summarization[C].In ACL/EACL-97 summarization workshop.Madrid,1997.
[Barzilay et al.2002]Barzilay R.,Elhadad N.,and McKeown K.R.Inferring Strategies for Sentence Ordering in Multidocument News summarization[J].Journal of Artificial Intelligence Research,volume 17,pages 35-55.2002.
[Barzilay and Lapata 2005]Barzilay R.and Lapata M.Modeling local coherence:An entity-based approach[C].In Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics(ACL'05).2005.
[Barzilay and Lapata 2007]Barzilay R.and Lapata M.Modeling local coherence:An entity-based approach[J].Computational Linguistics.To appear.2007.
[Barzilay and Lee 2004]Barzilay R.and Lee L.Catching the drift:Probabilistic content models,with applications to generation and summarization[C].In Proc.of the HLT-NAACL 2004:Proceedings of the Main Conference,(pp.113-120).2004.
[Barzilay and Mckeown 2005]Barzilay R.and Mckeown K.R.Sentence Fusion for Multidocument News Summarization[J].Computational Linguistics 31(3):297-328.2005.
[Baxendale 1958]Baxendale P.E.Machine-made index for technical literature-an experiment[J].IBM Journal of Research and Development,Vol.2,No.4.1958.
[Berger et al.1996]Berger,A.L.,Della Pietra,S.A.,and Della Pietra,V.J.A maximum entropy approach to natural language processing[J].Computational Lingustics,22(1),38-73.1996.
[Bollegala et al.2005a]Bollegala D.,Okazaki N.,and Ishizuka M.A Machine Learning Approach to Sentence Ordering for Multidocument Summarization and Its Evaluation[C].In Proceedings of International Joint Conference on Natural Language Processing 2005.pp.624-635.
[Bollegala et al.2005b]Bollegala D.,Okazaki N.,and Ishizuka M.A Clustering Based Approach to Sentence Ordering for Multidocument Summarization and its Evaluation[C].In Proceedingss of the 19th Annual Conference of the Japanese Society for Artificial Intelligence,2005.
[Bollegala et al.2006]Bollegala D.,Okazaki N,and Ishizuka M.A Bottom-up approach to sentence ordering for multi-document summarization[C].In Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the ACL,(pp.385-392).Sydney,Australia.2006.
[Budanitsky 1999]Budanitsky A.Lexical semantic relatedness and its application in natural language processing[R].Technical Report CSRG-390,University of Toronto,August 1999.
[Budanitsky and Hirst 2001]Budanitsky A.and Hirst G.Semantic distance in Word.Net:An experimental,application-oriented evaluation of five measures[C].In Proceedings of NAACL Workshop on WordNet and other lexical resources,pp.29-34.2001.
[Carbonell and Goldstein 1998]Carbonell,J.and Goidstein,J.The use of MMR,diversity-based reranking for reordering documents and producing summaries[C].In Proceedings of SIGIR 1998(pp.335-336).Melbourne,Australia.1998.
[Cohen et al.1999]Cohen William W.,Schapire Robert E.,and Singer Y.Learning to Order Things[J].Journal of Artificial Intelligence Research,1999.
[Collins 1997]Collins M.Three generative,lexicalised models for statistical parsing[C].In Proceedings of the ACL/EACL,16-23.1997.
[Conroy and Leary 2001]Conroy J.M.and Leary D.P.Text Summarization via Hidden Markov Models and Pivoted QR Matrix Decomposition[R].Technical report,University of Maryland,College Park,Maryland,March,2001.
[Conroy and Schlesinger 2005]Conroy J.M.and Schlesinger J.D.CLASSY query-based multi-document summarization[C].In Proceedings of DUC 2005.
[Dang 2005]Dang H.T..Overview of DUC 2005[C].In Proceedings of Document Understanding Conference 2005.
[Dang 2006]Dang H.T.Overview of DUC 2006[C].In Proceedings of Document Understanding Conference 2006.
[Daume and Marcu 2005a]Daume H.and Marcu D.Bayesian Summarization at DUC and a Suggestion for Extrinsic Evaluation[C].In Proceedings of Document Understanding Conference,2005.
[Daume and Marcu 2005b]Daume H.and Marcu D.Bayesian Multi-Document Summarization at MSE[C].In ACL 2005 Workshop on Intrinsic and Extrinsic Evaluation Measures.2005.
[Daume and Marcu 2006]Daume H.and Marcu D.Bayesian Query-Focused Summarization[C].In Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the ACL,pages 305-312.Sydney,July 2006.
[DUC]Document Understanding Conference.http://duc.nist.gov.
[Edmundson et al.1959]Edmundson H.P.,Oswald V.A.,and Wyllys R.E.Automatic Indexing and Abstracting of Contents of Documents[J].Planning Research Corporation,Los Angeles,California.1959.
[Eisner et al.2007]Eisner M,Austerweil J.,and Charniak E.A unified local and global model for discourse coherence[C].In proc.of NAACL 2007.
[Erkan and Radev 2004a]Erkan G.and Radev D.R.LexRank:Graph-based lexical centrality as salience in text summarization[J].Journal of Artificial Intelligence Research,22:457-479.2004.
[Erkan and Radev 2004b]Erkan G.and Radev D.R.LexPageRank:Prestige in Multi-Document Text Summarization[C].In Proceedings of EMNLP 2004.Barcelona,Spain.
[Erkan 2006]Erkan G.Using Biased Random Walks for Focused Summarization[CJ.In Proceedings of DUC 2006.
[Farzindar et al.2005]Farzindar A.,Rozon F.,and Lapalme G.CATS a topic-oriented multi-document summarization system at DUC 2005[C].In Proceedings of Document Understanding Conference 2005.
[Fellbaum 1998]Fellbaum C.WordNet:An electronic lexical database[M].MIT Press,1998
[Foltz et al.1998]Foltz P.W.,Kintsch W.,and Landauer T.K.Textual coherence using latent semantic analysis[J].Discourse Processes,25(2&3),285-307.1998.
[George et al.1993]George A.Miller,Richard Beckwith,Christiane Fellbaum.Introduction to WordNet:An On-line Lexical Database[J].International Journal of Lexicography,3:235-3121993.
[Goldensohn 2005]Goldensohn S.B.Columbia University at DUC 2005[C].In Proceedings of Document Understanding Conference 2005.
[Gong and Liu 2001]Gong Y.and Liu X.Generic Text Summarization Using Relevancce Measure and Latent Semantic Analysis[C].In Proceedings of SIGIR 2001.New Orleans,USA.2001.
[Good 1963]Good I.J.Maximum Entropy for Hypothesis Formulation,especially for Multidimensional Contingency Tables[J].In The Annals of Mathematical Statistics,34(3):911-934,1963
[Grosz et al.1995]Grosz,B.J.,Joshi,A.K.,and Weinstein,S.Centering:A framework for modeling the local coherence of discourse[J].Computational Linguistics,21(2):203-225.1995.
[Haveliwala 2002]Haveliwala T.H.Topic-Sensitive PageRank[C].In Proc.of WWW2002,May 7-11,2002,Honolulu,Hawaii,USA.
[Hirst and St-Onge 1998]Hirst G.and St-Onge D.Lexical chains as representations of context for the detection and correction of malapropisms[J].In Fellbaum 1998,pp.305-332.
[Hotho et al.2003]Hotho A.,Staab S.,and Stumme G.WordNet improves text document clustering[C].In Proc.of the SIGIR 2003 Semantic Web Workshop,2003.
[Hovy et al.2005]Hovy E.,Lin C-Y,and Zhou L.Evaluating DUC 2005 using Basic Elements [C].In Proc.of Document Understanding Conference 2005.
[Jiang and Conrath 1997]Jiang Jay J.and Conrath David W.Semantic similarity based on corpus statistics and lexical taxonomy[C].In Proceedings of International Conference on Research in Computational Linguistics,Taiwan.
[Joachims 2002]Joachims T.Optimizing search engines using clickthrough data[C].In Proceesings of KDD,133-142.2002.
[Kibble and Power 2004]Kibble R.and Power R.Optimising referential coherence in text generation[J].Computational Linguistics,30(4):401-416.2004.
[Kieinberg 1999]Kleinberg J.M.Authoritative sources in a hyperlinked environment[J].Journal of the ACM,46(5):604-632,1999.
[Knight and Marcu 2000]Knight K.and Marcu D.Statistics-Based Summarization-Step One:Sentence Compression[C].In Proceedings of AAAI 2000.
[Kupiec et al.1995]Kupiec J.,Pedersen J.,and Chen F.A Trainable Document Summarizer[C].In Proceedings of the Eighteenth Annual International ACM Conference on Research and Development in Information Retrieval(SIGIR),68-73.Seattle,WA.1995.
[Lacatusu et al 2005]Lacatusu F.,Hickl A.,Aarseth P.,and Taylor L.Lite-GISTexter at DUC 2005[C].In Proc.of DUC 2005.
[Lafferty and Zhai 2001]Lafferty J.and Zhai C.Document language models,query models,and risk minimization for information retrieval[C].In Proceedings of the Conference on Research and Developments in Information Retrieval(SIGIR).2001.
[Landauer and Dumais 1997]Landauer T.K.and Dumais S.T.A solution to Plato's problem:The latent semantic analysis theory of acquisition,induction and representation of knowledge [J].Psychological Review,104(2):211-240.1997.
[Lapata 2003]Lapata M.Probabilistic text structuring:Experiments with sentence ordering[C].In Proceedings of the 41st Annual Meeting of the Association for Computational Linguistics,(pp.545-552).Sapporo,Japan.2003.
[Lapata and Barzilay 2005]Lapata M.and Barzilay R.Automatic evaluation of text coherence:Models and representations[C].In Proc.of the 19th International Joint Conference on Artificial Intelligence(IJCAI-05),(pp.1085-1090).2005.
[Lavrenko et al.2002]Lavrenko V.,Choquette M.,and Croft B.Crosslingual re&vance models [C].In Proceedings of the Conference on Research and Developments in Information Retrieval(SIGIR).2002.
[Leacock and Chodorow 1998]Leacock C.and Chodorow M.Combining local context and WordNet similarity for word sense identification[J].In Fellbaum 1998,pp.265-283.
[Li et al.2005]Li W.,Li W.,Li B.,Chen Q.,and Wu M.The Hong Kong Polytechnic University at DUC2005[C].In Proceedings of Document Understanding Conference 2005.
[Lin 1998]Lin D.An information-theoretic definition of similarity[C].In Proceedings of the 15th International Conference on Machine Learning,Madison,WI.1998.
[Lin 2001]Lin C.Y,Summary Evaluation Environment.http://www.isi.edu/～cyl/SEE.
[Lin 2004]Lin C.Y.ROUGE:A Package for Automatic Evaluation of Summaries[C].In Proceedings of Workshop on Text Summarization Branches Out,Post-conference Workshop of ACL 2004,Barcelona,Spain.2004.
[Lin and Hovy 2003]Lin C.Y.and Hovy E.Automatic evaluation of summaries using n-gram co-occurrence[C].In Proceedings of HLT-NAACL 2003.Edmonton,Canada.2003.
[Liu et al.2004]Liu Y.,et al.Affinity Rank." A New Scheme for Efficient Web Search[C].In Proceedings of WWW 2004,May 17-22,2004,New York,USA.
[Luhn 1958]Luhn H.P.The automatic creation of literature abstract[J].IBM Journal of Research and Development.1958,2(2):159-165.
[Mani et al.1998]Mani I.,Bloedom E.,and Gates B.Using cohesion and coherence models for text summarization[C].In Proceedings of AAAI Spring Symposium on Intelligent Text Summarization,Stanford(pp.69-76).1998.
[Mani 2001]Mani J.Automatic Summarization[M].Amsterdam/Philadephia:John Benjamins Publishing Company.2001.
[Mann and Thompson 1988]Mann,W.C.& Thompson,S.A.Rhetorical structure theory:Toward a functional theory of text organization[J].Text,8,3,243-281.1988.
[Marcu 1997]Marcu D.From local to global coherence:A bottom-up approach to text planning [C].In Proceedings of the 14th National Conference on Artificial Intelligence,(pp.629-635).Providence,Rhode Island.1997.
[Mckeown et al.1999]Mckeown K.,Klavans J.,Hatzivassiloglou V.,Barzilay R.,and Eskin E.Towards Multidocument Summarization by Reformulation:Progress and Prospects[C].In Proceedings of AAAI 1999.
[Mihalcea and Tarau 2004]Mihalcea,R.and Tarau,P.TextRank:Bringing order into texts[C].In Proceedings of EMNLP 2004(pp.404-411).Barcelona,Spain.
[Miller et al.1993]Miller G.,Beekwith R.,Fellbaum C.,Gross D.,and Miller K.J.Five Papers on WordNet[R].Technical Report,Princeton University,1993.
[Miltsakaki and Kukichy 2000]Miltsakaki E.and Kukichy K.Automated evaluation of coherence in student essays[C].In Proceedings of the Workshop on Language Resources and Tools in Educational Applications,Athens(pp.7-14).2000.
[Molina 1995]Molina P.Document abstracting:Toward a methodological model[J].Journal of the American Society for Information Science 46(3).1995.
[Morris et al.1992]Morals A,Kasper G,and Adams D.The Effects and Limitations of Automatic Text Condensation on Reading Comprehension Performance[J].Information Systems Research, 26:17-35.1992.
[Motwani and Raghavan 1995] Motwani R. and Raghavan P. Randomized Algorithms [MJ. Cambridge University Press, United Kingdom, 1995.
[Nenkova and Passonneau 2004] Nenkova A. and Passonneau R. Evaluating Content Selection in Summarization: The Pyramid Method [C]. In Proc. of NAACL-HLT 2004.
[Ng and Cardie 2002] Ng V. and Cardie C. Improving machine learning approaches to coreference resolution [CJ. In Proceedings of the ACL, 104-111.2002.
[Nie et al. 2006] Nie L., Davison B. D., and Qi X. Topical Link Analysis for Web Search [C]. In Proceedings of SIGIR'06, August 6-11,2006, Seattle, Washington, USA.
[Okazaki et al. 2004] Okazaki N, Matsuo Y., and Ishizuka M. Improving chronological sentence ordering by precedence relation [C]. In Proceedings of 20th International Conference on Computational Linguistics (COLING 04), (pp. 750-756). 2004.
[Otterbacher et al. 2005] Otterbacher J., Erkan G., and Radev D. R. Using random walks for question-focused sentence retrieval [CJ. In Proc. of HLT-EMNLP 2005. Vancouver, BC.
[Page et al. 1998] Page L., Brin S., Rajeev M., and Terry W. The PageRank citation ranking: Bringing order to the web [RJ. Technical report, Stanford University, Stanford, CA. 1998.
[Papineni et al. 2001] Papineni, K., S. Roukos, T. Ward, and Zhu W. J. BLEU: a Method for Automatic Summarization of Machine Translation [RJ. IBM Research Report RC22176(W0109-022). 2001.
[Pietra et al. 1997] Pietra S. D., Pietra V. D., Lafferty J. Inducing Features of Random Fields [J]. In IEEE Transactions on Pattern Analysis and Machine Intelligence, 19(4): 380-393,1997.
[Ponte and Croft 1998] Ponte J. M. and Croft B. A language modeling approach to information retrieval [CJ. In Proceedings of the Conference on Research and Developments in Information Retrieval (SIGIR). 1998.
[Radev et al. 2000] Radev D. R., Jing H., and Budzikowska M. Summarization of multiple documents: clustering, sentence extraction, and evaluation [CJ. In Proceedings of ANLP-NAACL Workshop on Automatic Summarization, 21-30. Seattle, WA, 2000.
[Radev et al. 2004] Radev, D. R., Jing, H. Y., Stys, M., and Tam, D. Centroid-based summarization of multiple documents [J]. Information Processing and Management, 40, 919-938. 2004.
[Rau et al.1989]Rau L.F.,Jacobs P.S.,and Zemik U.Information Extraction and Text Summarization Using Linguistic Knowledge Acquisition[J].Information Processing and Management.Vol.25,No.4.1989.
[Resnik 1995]Resnik P.Using information content to evaluate semantic similarity[C].In Proceedings of the 14th International Joint Conference on Artificial Intelligence,pages 448-453,Montreal.
[Richardson and Domingos 2002]Richardson M.and Domingos P.The Intelligent Surfer:Probabilistic Combination of Link and Content Information in PageRank[C].In Proceedings of NIPS 2002.
[Rush et al.1971]Rush J.E.,Salvador R.,and Zamora A.Automatic abstracting and indexing.Ⅱ:Production of indicative abstracts by application of contextual inference and syntactic coherence criteria[J].Journal of the American Society for Information Science,Vol;.22,No.4.
[Salton and McGill 1983]Salton G.and McGill M.J.Introduction to Modern Information Retrieval[M].New York:McGraw-Hill.1983.
[Seco et al.2004]Seco N.,Veale T.,and Hayes J.An intrinsic information content metric for semantic similarity in WordNet[C].In Proceedings of the 16th European Conference on Artificial Intelligence.Valencia,Spain.2004.
[Soricut and Marcu 2006]Soricut R.and Marcu D.Discourse generation using utility-trained coherence models[C].In Proceedings of the Association for Computational Linguistics Conference(ACL-2006).
[Soubbotin and Soubbotin 2005]Soubbotin M.and Soubbotin S.Trade-Off between Factors Influencing Quality of the Summary[C].In Proceedings of Document Understanding Conference 2005.
[Spark and Galliers 1996]Spark J.K.and Galliers J R.Evaluating Natural Language Processing:An Analysis and Review[M].New York:Springer.1996.
[Teufel and Moens 1997]Teufel S.and Moens M.Sentence Extraction as a Classification Task [C].In Proceedings of the Workshop on Intelligent Scalable Summarization.ACL/EACL Conference,58-65.Madrid,Spain.1997.
[Vandeghinste and Pan 2004]Vandeghinste V.and Pan Y.Sentence Compression for Automated Subtitling:A Hybrid Approach[C].In Proceedings of ACL 2004.
[Wan et al.2007a]Wan X.,Yang J.,and Xiao J.CollabSum:Exploiting Multiple Document Clustering for Collaborative Single Document Summarizations[C].In Proceedings of SIGIR'07,July 23-27,2007,Amsterdam,The Netherlands.
[Wan et al.2007b]Wan X.,Yang J.,and Xiao J.Towards an iterative reinforcement approach for simultaneous document summarization and keyword extraction[C].In Proceedings of ACL 2007(pp.552-559).2007.
[Wan et al.2007c]Wan X.,Yang J,and Xiao J.Manifold-ranking based topic-focused multi-document summarization[C].In Proceedings of IJCAI 2007(pp.2903-2908).2007.
[Zhang et al.2005]Zhang Benyu.et al.Improving web search results using affinity graph[C].In Proceedings of SIGIR 2005.Salvador,Brazil.
[Zhou et ai.2005]Zhou L,Lin C-Y,and Hovy E.A BE-based multi-document summarizer with query interpretation[C].In Proc.of DUC 2005.
[陈2005]陈宁昱 周雅倩 黄萱菁 吴立德.利用未标注语料改进实体名识别性能[J].中文信息学报.Vol 19.No 2.2005:7-11.
[郭2002]郭燕慧 钟义信 马志勇 姚均勇.自动文摘综述[J].情报学报.21(5).2002.
[李2000]李蕾 郭祥昊 钟义信.面向特定领域的理解型中文自动文摘系统[J].计算机研究与发展,37(4):6-10.2000.
[刘1995]刘挺 吴岩 王开铸.基于信息抽取和文本生成的自动文摘系统设计[J].情报学报.16(增刊).1995.
[王1997]王永成 徐慧.OA中文文献自动摘要系统[J].情报学报.16(2).1997.
[吴1997]吴立德等.大规模中文文本处理[M].上海:复旦大学出版社.1997.
[姚1995]姚天顺等.自然语言理解--一种让机器懂得人类语言的研究[M].清华大学出版社,广西科学技术出版社.1995.
© 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 |