We use cookies to improve your experience with our site.

Indexed in:

SCIE, EI, Scopus, INSPEC, DBLP, CSCD, etc.

Submission System
(Author / Reviewer / Editor)
Advanced Search
Volume 26 Issue 1
December  2010
Turn off MathJax
Article Contents
Abstract
References
Related Articles
Guo-Dong Zhou, Fang Kong. Learning Noun Phrase Anaphoricity in Coreference Resolution via Label Propagation[J]. Journal of Computer Science and Technology, 2011, 26(1): 34-44. DOI: 10.1007/s11390-011-1109-8
Citation: Guo-Dong Zhou, Fang Kong. Learning Noun Phrase Anaphoricity in Coreference Resolution via Label Propagation[J]. Journal of Computer Science and Technology, 2011, 26(1): 34-44. DOI: 10.1007/s11390-011-1109-8
shu

Learning Noun Phrase Anaphoricity in Coreference Resolution via Label Propagation

  • NLP Lab, School of Computer Science and Technology, Soochow University, Suzhou 215006, China

Funds: Supported by the National Natural Science Foundation of China under Grant Nos. 60873150, 90920004 and 61003153.
More Information
  • Author Bio:

    Guo-Dong Zhou received the Ph.D. degree from the National University of Singapore in 1999. He joined the Institute for Infocomm Research, Singapore, in 1999, and had been an associate scientist, scientist and associate lead scientist at the institute until August 2006. Currently, he is a professor at the School of Computer Science and Technology, Soochow University, Suzhou, China. His research interests include natural language processing, information extraction and machine learning. He is a senior member of CCF and has been the member of ACM and IEEE since 1999.

    Fang Kong received her Ph.D. degree from Soochow University, Suzhou, China, in 2009. Currently, she is an associate professor at the university. Her research interests include natural language processing and information extraction. She is a member of CCF.

  • Received Date: December 27, 2009
  • Revised Date: October 27, 2010
  • Published Date: December 31, 2010
    Abstract
  • Knowledge of noun phrase anaphoricity might be profitably exploited in coreference resolution to bypass the resolution of non-anaphoric noun phrases. However, it is surprising to notice that recent attempts to incorporate automatically acquired anaphoricity information into coreference resolution systems have been far from expectation. This paper proposes a global learning method in determining the anaphoricity of noun phrases via a label propagation algorithm to improve learning-based coreference resolution. In order to eliminate the huge computational burden in the label propagation algorithm, we employ the weighted support vectors as the critical instances to represent all the anaphoricity-labeled NP instances in the training texts. In addition, two kinds of kernels, i.e., the feature-based RBF (Radial Basis Function) kernel and the convolution tree kernel with approximate matching, are explored to compute the anaphoricity similarity between two noun phrases. Experiments on the ACE2003 corpus demonstrate the great effectiveness of our method in anaphoricity determination of noun phrases and its application in learning-based coreference resolution.
    • FullText(HTML)
    • References (31)
  • [1]
    Soon W M, Ng H T, Lim D. A machine learning approach o coreference resolution of noun phrase. Computational Linuistics, 2001, 27(4): 521-544.
    [2]
    Ng V, Cardie C. Improving machine learning approaches to oreference resolution. In Proc. ACL 2002, Philadelphia, SA, Jul. 6-12, 2002, pp.104-111.
    [3]
    Strube M, Muller C. A machine learning approach to pronoun esolution in spoken dialogue. In Proc. ACL 2003, Sapporo, apan, Jul. 7-12, 2003, pp.68-175.
    [4]
    Yang X F, Zhou G D, Su J, Chew C L. Coreference resolution sing competition learning approach. In Proc. ACL 2003, apporo, Japan, Jul. 7-12, 2003, pp.177-184.
    [5]
    Yang X F, Su J, Lang J, Tan C L, Liu T, Li S. An entityention model for coreference resolution with inductive logic rogramming. In Proc. ACL 2008, Columbus, USA, Jun. 15-20, 2008, pp.843-851.
    [6]
    Paice C D, Husk G D. Towards the automatic recognition of naphoric features in English text: The impersonal pronoun it. Computer Speech and Language, 1987, 2(2): 109-132.
    [7]
    Lappin S, Leass H J. An algorithm for pronominal anaphora esolution. Computational Linguistics, 1994, 20(4): 535-561.
    [8]
    Kennedy C, Boguraev B. Anaphora for everyone: Pronoinal anaphora resolution without a parser. In Proc. COLNG 1996, Copenhagen, Denmark, Aug. 5-9, 1996, pp.113-118.
    [9]
    Denber M. Automatic resolution of anaphora in English. echnical Report, Eastman Kodak Co. 1998.
    [10]
    Vieira R, Poesio M. An empirically based system for processng definite descriptions. Computational Linguistics, 2000, 7(4): 539-592.
    [11]
    Bean D, Riloff E. Corpus-based identification of nonnaphoric noun phrases. In Proc. ACL 1999, University of aryland, College Park, USA, Jun. 20-26, 1999, pp.373-380.
    [12]
    Bergsma S, Lin D K, Goebel R. Distributional identification f non-referential pronouns. In Proc. ACL 2008, Columbus, SA, Jun. 15-20, 2008, pp.10-18.
    [13]
    Evans R. Applying machine learning toward an automatic lassification of it. Literary and Linguistic Computing, 2001, 6(1): 45-57.
    [14]
    Ng V, Cardie C. Identifying anaphoric and non-anaphoric oun phrases to improve coreference resolution. In Proc. OLING 2002, Taipei, China, Aug. 24-Sept. 1, 2002, pp.730-736.
    [15]
    Ng V. Learning noun phrase anaphoricity to improve confernce resolution: Issues in representation and optimization. In Proc. ACL 2004, Barcelona, Spain, Jul. 21-26, 2004, pp.151-158.
    [16]
    Yang X F, Su J, Tan C L. A twin-candidate model of coreerence resolution with non-anaphor identification capability. In Proc. IJCNLP 2005, Jeju Island, Korea, Oct. 11-13, 2005, p.719-730.
    [17]
    Denis P, Baldridge J. Joint determination of anaphoricity and oreference using integer programming. In Proc. NAACLLT2007, Rochester, USA, Apr. 22-27, 2007, pp.236-243.
    [18]
    Cherry C, Bergsma S. An expectation maximization approach o pronoun resolution. In Proc. CoNLL 2005, Ann Arbor, SA, Jun. 29-30, 2005, pp.88-95.
    [19]
    Zhu X, Ghahramani Z. Learning from labeled and unlabeled ata with label propagation. CMU CALD Technical Report, MU-CALD-02-107, 2002.
    [20]
    Charniak E. Immediate-head parsing for language models. In Proc. ACL 2001, Toulouse, France, Jul. 9-11, 2001, pp.129-137.
    [21]
    Yang X F, Su J, Tan C L. Kernel-based pronoun resolution ith structured syntactic knowledge. In Proc. COLINGCL 2006, Sydney, Australia, Jul. 17-21, 2006, pp.41-48.
    [22]
    Zhou G D, Kong F, Zhu Q M. Context-sensitive convolution ree kernel for pronoun resolution. In Proc. IJCNLP 2008, yderabad, India, Jan. 7-12, 2008, pp.25-31.
    [23]
    Yang X F, Su J, Tan C L. A twin-candidate model for earning-based anaphora resolution. Computational Linguisics, 2008, 34(3): 327-356.
    [24]
    Haussler D. Convolution kernels on discrete structures. Techical Report UCS-CRL-99-10, University of California, Santa ruz, USA, 1999.
    [25]
    Collins M, Duffy N. Convolution kernels for natural language. In Proc. NIPS 2001, Vancouver, Canada, Dec. 3-8, 2001, p.625-632.
    [26]
    Zhang M, Che W X, Aw A T, Tan C L, Zhou G D, Liu T, Li . A grammar-driven convolution tree kernel for semantic role lassification. In Proc. ACL 2007, Prague, Czech Republic, un. 23-30, 2007, pp.200-207.
    [27]
    Moschitti A. Efficient convolution kernels for dependency and onstituent syntactic trees. In Proc. ECML2006, Berlin, ermany, Sept. 18-22, 2006, pp.318-329.
    [28]
    Zhou G D, Su J. Error-driven HMM-based chunk tagger with ontext-dependent lexicon. In Proc. EMNLP-VLC 2000, ong Kong, China, Oct. 7-8, 2000, pp.71-79.
    [29]
    Zhou G D, Su J. Named entity recognition using an HMMased chunk tagger. In Proc. ACL 2002, Philadelphia, USA, ul. 6-12, 2002, pp.473-480.
    [30]
    Joachims T. Text categorization with support vector machine: earning with many relevant features. In Proc. ECML1998, hemnitz, Germany, Apr. 21-23, 1998, pp.137-142.
    [31]
    Vilain M, Burger J, Aberdeen J, Connolly D, Hirschman L. A odel theoretic coreference scoring scheme. In Proc. MUC-6, olumbia, USA, Nov. 1-3, 1995, pp.45-52.
    • Relative Articles

  • Related Articles

    [1]Qi-Guo Dai, Mao-Zu Guo, Xiao-Yan Liu, Zhi-Xia Teng, Chun-Yu Wang. CPL: Detecting Protein Complexes by Propagating Labels on Protein-Protein Interaction Network[J]. Journal of Computer Science and Technology, 2014, 29(6): 1083-1093. DOI: 10.1007/s11390-014-1492-z
    [2]Wei Wu, Hang Li, Yun-Hua Hu, Rong Jin. A Kernel Approach to Multi-Task Learning with Task-Specific Kernels[J]. Journal of Computer Science and Technology, 2012, 27(6): 1289-1301. DOI: 10.1007/s11390-012-1305-1
    [3]Guo-Dong Zhou, Qiao-Ming Zhu. Kernel-Based Semantic Relation Detection and Classification via Enriched Parse Tree Structure[J]. Journal of Computer Science and Technology, 2011, 26(1): 45-56. DOI: 10.1007/s11390-011-1110-2
    [4]Kilho Shin, Tetsuji Kuboyama. A Generalization of Haussler's Convolution Kernel &mdash|Mapping Kernel and Its Application to Tree Kernels[J]. Journal of Computer Science and Technology, 2010, 25(5): 1040-1054. DOI: 10.1007/s11390-010-1082-7
    [5]Lei Jia, Shi-Zhong Liao, Li-Zhong Ding. Learning with Uncertain Kernel Matrix Set[J]. Journal of Computer Science and Technology, 2010, 25(4): 709-727. DOI: 10.1007/s11390-010-1055-x
    [6]Lin Xueyin, Chen Xiangrong, Zhu Zhigang, Shi Dingji. Range Information Propagation Transform[J]. Journal of Computer Science and Technology, 1998, 13(5): 438-447.
    [7]Wang Hui, Liu Dayou, Wang Yafei. Sequential Back-Propagation[J]. Journal of Computer Science and Technology, 1994, 9(3): 252-260.
    [8]Xu Meirui, Liu Xiaolin. A VLSI Algorithm for Calculating the Tree to Tree Distance[J]. Journal of Computer Science and Technology, 1993, 8(1): 68-76.
    [9]Xue Xing, Sun Zhongxiu, Zhou Jianqiang, Xu Xihao. A Message-Based Distributed Kernel for a Full Heterogeneous Environment[J]. Journal of Computer Science and Technology, 1990, 5(1): 47-56.
    [10]Zhang Cui, Zhao Qinping, Xu Jiafu. Kernel Language KLND[J]. Journal of Computer Science and Technology, 1986, 1(3): 65-79.
    • Supplements (0)

Catalog

    Get Citation
    PDF
    XML
    Article views (27) PDF downloads (2092) Cited by()
    Related

    Copyright ©2025 JCST, All Rights Reserved     京ICP备05002829号-1

    Institute of Computing Technology, Chinese Academy of Sciences
    P.O. Box 2704, Beijing 100190, P.R. China

    Tel.: 86-10-62610746 E-mail: jcst@ict.ac.cn

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return