共指消解研究方法综述
详细信息    查看全文 | 推荐本文 |
  • 英文篇名:A Survey of Coreference Resolution Research Methods
  • 作者:宋洋 ; 王厚峰
  • 英文作者:SONG Yang;WANG Houfeng;Key Laboratory of Computational Linguistics(Ministry of Education),Peking University;
  • 关键词:共指消解 ; 指代消解 ; 有指导学习 ; 无指导学习
  • 英文关键词:coreference resolution;;anaphora resolution;;supervised learning;;unsupervised learning
  • 中文刊名:MESS
  • 英文刊名:Journal of Chinese Information Processing
  • 机构:北京大学计算语言学教育部重点实验室;
  • 出版日期:2015-01-15
  • 出版单位:中文信息学报
  • 年:2015
  • 期:v.29
  • 基金:国家自然科学基金(61370117,61333018);; 国家社科重大项目(12&ZD227)
  • 语种:中文;
  • 页:MESS201501001
  • 页数:12
  • CN:01
  • ISSN:11-2325/N
  • 分类号:5-16
摘要
共指消解作为自然语言处理中的一个重要问题一直受到学术界的重视。二十多年来,基于规则的和基于统计的不同方法被提出,在一定程度上推进了该问题研究的发展,并取得了大量研究成果。该文首先介绍了共指消解问题的基本概念,并采用形式化的方法对该问题做了描述;然后,针对国内外近年来在共指消解研究中的方法进行了总结;之后,对共指消解中重要的特征问题进行了分析与讨论;最后,历数了共指消解的各种国际评测,并对未来可能的研究方向进行了展望。
        Coreference resolution,as a challenging issue,has been noted by NLP researchers for a long time.In recent twenty years,many kinds of advanced NLP techniques have been applied on this problem,and some of them have achieved significant improvements.In this paper,we first introduce some basic concepts and formalized this isuse.Then we summarize different research strategies adopted by researchers in recent decades.We highlight the feature engineering,which lies in the core of coreference resolution.Finally we describe the recent evaluations for this task and discusssome key issues and prospects in the future.
引文
[1]郎君,秦冰,刘挺,等.篇章共指消解研究综述[J].汉语语言与计算学报,2007,17(4):227-253.
    [2]王厚峰.指代消解的基本方法和实现技术[J].中文信息学报,2002,16(6):9-17.
    [3]J.R.Hobbs.Resolving pronoun references[J].Journal of Lingua,1978,44:311-338.
    [4]A.Haghighi,D.Klein.Simple coreference resolution with rich syntactic and semantic features[C]//Proceedings of the 2009Conference on Empirical Methods in Natural Language Processing(EMNLP),2009:1152-1161.
    [5]B.Grosz,A.Joshi,S.Weinstein.Centering:A framework for modelling the local coherence of discourse[J].Journal of Computational Linguistics,1995,21(2):203-225.
    [6]Susan E.Brennan,Marilyn W.Friedman,Carl Pollard.A centering approach to pronouns[C]//Proceedings of the 25th Annual Meeting of the Association for Computational Linguistics(ACL),1987:155-162.
    [7]M.Poesio,R.Stevenson,Barbara Di Eugenio,et al.Centering:A parametric theory and its instantiations[J].Journal of Computational Linguistics,2004,30(3):309-363.
    [8]S.Lappin,H.J.Leass.An algorithm for Pronominal Anaphora Resolution[J].Journal of Computational Linguistics,1994,20(4):535-561.
    [9]C.Kennedy,B.Boguraev.Anaphora for everyone:Pronominal anaphora resolution without a parser[C]//Proceedings of the 16th International Conference on Computational Linguistics(COLING),1996:113-118.
    [10]R.Mitkov.Robust pronoun resolution with limited knowledge[C]//Proceedings of the 36th Annual Meeting of the Association for Computational Linguistics and 17th International Conference on Computational Linguistics(COLING-ACL),1998:869-875.
    [11]K.Raghunathan,H.Lee,S.Rangarajan,et al.A multi-pass sieve for coreference resolution[C]//Proceedings of the 2010Conference on Empirical Methods in Natural Language Processing(EMNLP),2010.
    [12]H.Lee,Y.Peirsman,A.Chang,et al.Stanford’s multi-pass sieve coreference resolution system at the conll-2011shared task[C]//Proceedings of the Fifteenth Conference on Computational Natural Language Learning:Shared Task,2011:28-34.
    [13]V.Ng,C.Cardie.Bootstrapping coreference classifiers with multiple machine learning algorithms[C]//Proceedings of the 2003 Conference on Empirical Methods in Natural Language Processing(EMNLP),2003:113-120.
    [14]O.Uryupina,S.Saha,A.Ekbal,et al.Multi-metric optimization for coreference:The unitn/iitp/essex submission to the 2011conll shared task[C]//Proceedings of the Fifteenth Conference on Computational Natural Language Learning:Shared Task,2011:61-65.
    [15]V.Ng.Graph-cut-based anaphoricity determination for coreference resolution[C]//Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies(HLT-NAACL),2009:575-583.
    [16]Guodong Zhou,Fang Kong.Global learning of noun phrase anaphoricity in coreference resolution via label propagation[C]//Proceedings of the 2009Conference on Empirical Methods in Natural Language Processing(EMNLP),2009:978-986.
    [17]孔芳,朱巧明,周国栋.中英文指代消解中待消解项识别的研究[J].计算机研究与发展,2012,49(5):1072-1085.
    [18]J.McCarthy,W.Lehnert.Using decision trees for coreference resolution[C]//Proceedings of the 14th International Joint Conference on Artificial Intelligence,1995.
    [19]Wee Meng Soon,Hwee Tou Ng,Chung Yong Lim.A machine learning approach to coreference resolution of noun phrases[J].Computational Linguistics,2001,27(4):521-544.
    [20]E.Bengtson,D.Roth.Understanding the value of features for coreference resolution[C]//Proceedings of the 2008Conference on Empirical Methods in Natural Language Processing(EMNLP),2008.
    [21]V.Ng,C.Cardie.Improving machine learning approaches to coreference resolution[C]//Proceedings of the Annual Meeting of the Association for Computational Linguistics(ACL),2002:104-111.
    [22]C.Gasperi.Active learning for anaphora resolution[C]//Proceedings of the NAACL HLT 2009 Workshop on Active Learning for Natural Language Processing,2009.
    [23]Niyu Ge,J.Hale,E.Charniak.A statistical approach to anaphora resolution[C]//Proceedings of the ACL 1998 Workshop on Very Large Corpora,1998.
    [24]Xiaoqiang Luo,A.Ittycheriah,Hongyan Jing,et al.A mention-synchronous coreference resolution algorithm based on the bell tree[C]//Proceedings of the Annual Meeting of the Association for Computational Linguistics(ACL),2004:135-142.
    [25]S.P.Ponzetto,Michael Strube.Exploiting semantic role labeling,wordnet and wikipedia for coreference resolution[C]//Proceedings of the main conference on Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics(HLT-NAACL),2006:192-199.
    [26]A.Rahman,V.Ng.Supervised models for coreference resolution[C]//Proceedings of the 2009Conference on Empirical Methods in Natural Language Processing(EMNLP),2009:968-977.
    [27]Y.Versley,A.Moschitti,M.Poesio,et al.Coreference systems based on kernels methods[C]//Proceedings of the 22nd International Conference on Computational Linguistics(COLING),2008:961-968.
    [28]J.R.Finkel,C.D.Manning.Enforcing transitivity in coreference resolution[C]//Proceedings of the Annual Meeting of the Association for Computational Linguistics(ACL),2008:45-48.
    [29]Shujian Huang,Yabing Zhang,Junsheng Zhou,et al.Coreference resolution using markov logic networks[C]//Proceedings of the 10th International Conference Computational Linguistics and Intelligent Text Processing(CICLing),2009.
    [30]刘未鹏,周俊生,黄书剑,等.基于有监督关联聚类的中文共指消解[J].计算机科学,2009,36(9):182-185.
    [31]C.Nicolae,G.Nicolae.Bestcut:A graph algorithm for coreference resolution[C]//Proceedings of the2006 Conference on Empirical Methods in Natural Language Processing(EMNLP),2006:275-283.
    [32]周俊生,黄书剑,陈家骏,等.一种基于图划分的无监督汉语指代消解算法[J].中文信息学报,2007,21(2):77-82.
    [33]谢永康,周雅倩,黄萱菁.一种基于谱聚类的共指消解方法[J].中文信息学报,2009,23(3):10-16.
    [34]Marc B.Vilain,John D.Burger,John S.Aberdeen,et al.A model-theoretic coreference scoring scheme[C]//Proceedings of the Sixth Message Understanding Conference(MUC),1995:45-52.
    [35]A.Bagga,B.Baldwin.Algorithms for scoring coreference chains[C]//Proceedings of the First International Conference on Language Resources and Evaluation Workshop on Linguistics Coreference,1998:563-566.
    [36]Xiaoqiang Luo.On coreference resolution performance metrics[C]//Proceedings of the joint conference on human language technology and empirical methods in natural language processing(HLT-EMNLP),2005:25-32.
    [37]Xiaofeng Yang,Jian Su,Jun Lang,et al.An entitymention model for coreference resolution with inductive logic programming[C]//Proceedings of the Annual Meeting of the Association for Computational Linguistics(ACL),2008:843-851.
    [38]Xiaofeng Yang,Guodong Zhou,Jian Su,et al.Coreference resolution using competition learning approach[C]//Proceedings of the Annual Meeting of the Association for Computational Linguistics(ACL),2003:176-183.
    [39]Xiaofeng Yang,Jian Su,Chew Lim Tan.A twincandidate model for learning-based anaphora resolution[J].Computational Linguistics,2008,34(3):327-356.
    [40]T.Joachims.Optimizing search engines using clickthrough data[C]//Proceedings of the ACM Conference on Knowledge Discovery and Data Mining(KDD),2002.
    [41]A.Rahman,V.Ng.Narrowing the modeling gap:A cluster-ranking approach to coreference resolution[J].Journal of Artificial Intelligence Research(JAIR),2011:469-521.
    [42]C.Cardie,K.Wagstaff.Noun phrase coreference as clustering[C]//Proceedings of the 1999 Conference on Empirical Methods in Natural Language Processing(EMNLP),1999.
    [43]K.Wagstaff,C.Cardie.Clustering with instancelevel constraints[C]//Proceedings of the Seventeenth International Conference on Machine Learning(ICML),2000:1103-1110.
    [44]A.Haghighi,D.Klein.Unsupervised coreference resolution in a nonparametric bayesian model[C]//Proceedings of the Annual Meeting of the Association for Computational Linguistics(ACL),2007,45:848.
    [45]Vincent Ng.Unsupervised models for coreference resolution[C]//Proceedings of the 2008 Conference on Empirical Methods in Natural Language Processing(EMNLP),2008:640-649.
    [46]H.Poon,P.Domingos.Joint unsupervised coreference resolution with markov logic[C]//Proceedings of the 2008Conference on Empirical Methods in Natural Language Processing(EMNLP),2008:650-659.
    [47]A.Haghighi,D.Klein.Coreference resolution in a modular,entity-centered model[C]//Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies(HLT-NAACL),2010:385-393.
    [48]Xiaofeng Yang,Jian Su,Chew Lim Tan.Kernelbased pronoun resolution with structured syntactic knowledge[C]//Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics(ACL),2006:41-48.
    [49]Fang Kong,Guodong Zhou.A tree kernel-based unified framework for chinese zero anaphora resolution[C]//Proceedings of the 2010Conference on Empirical Methods in Natural Language Processing(EMNLP),2010:882-891.
    [50]孔芳,周国栋.基于树核函数的中英文代词消解[J].软件学报,2012,23(5):1085-1099.
    [51]Véronique H.Optimization Issues in Machine Learning of Coreference Resolution[D].PhD thesis,University of Antwerp,2005.
    [52]S.Saha,A.Ekbal,O.Uryupina,et al.Single and multi-objective optimization for feature selection in anaphora resolution[C]//Proceedings of 5th International Joint Conference on Natural Language Processing(IJCNLP),2011:93-101.
    [53]E.Sapena,Lluís Padró,J.Turmo.Relaxcor participation in conll shared task on coreference resolution[C]//Proceedings of the Fifteenth Conference on Computational Natural Language Learning:Shared Task,2011:35-39.
    [54]K.Chang,R.Samdani,A.Rozovskaya,et al.Inference protocols for coreference resolution[C]//Proceedings of the Fifteenth Conference on Computational Natural Language Learning:Shared Task,2011:40-44.
    [55]E.Fernandes,Cícero dos Santos,Ruy Milidiú.Latent structure perceptron with feature induction for unrestricted coreference resolution[C]//Proceedings of the Joint Conference on EMNLP and CoNLL Shared Task,2012:41-48.
    [56]S.Martschat,Jie Cai,S.Broscheit,et al.A multigraph model for coreference resolution[C]//Proceedings of the Joint Conference on EMNLP and CoNLL Shared Task,2012:100-106.
    [57]Anders Bjrkelund,Richárd Farkas.Data-driven multilingual coreference resolution using resolver stacking[C]//Proceedings of the Joint Conference on EMNLP and CoNLL-Shared Task,2012:49-55.
    [58]Chen Chen,Vincent Ng.Combining the best of two worlds:A hybrid approach to multilingual coreference resolution[C]//Proceedings of the Joint Conference on EMNLP and CoNLL-Shared Task,2012:56-63.
    [59]Bo Yuan,Qingcai Chen,Yang Xiang,et al.A mixed deterministic model for coreference resolution[C]//Proceedings of the Joint Conference on EMNLP and CoNLL Shared Task,2012:76-82.
    [60]Pascal Denis,Jason Baldridge.Joint determination of anaphoricity and coreference resolution using integer programming[C]//Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies(HLT-NAACL),2007:236-243.
    [61]T.Finley,T.Joachims.Supervised clustering with support vector machines[C]//Proceedings of the International Conference on Machine Learning(ICML),2005:217-224,.
    [62]A.McCallum,B.Wellner.Conditional models of identity uncertainty with application to noun coreference[C]//Proceedings of Neural Information Processing Systems(NIPS),2004:905-912.
    [63]Yang Song,Jing Jiang,Wayne Xin Zhao,et al.Joint learning for coreference resolution with markov logic[C]//Proceedings of the conference on Empirical Methods in Natural Language Processing and Natural Language Learning(EMNLP-CoNLL),2012:1245-1254.
    [64]S.Bergsma.Automatic acquisition of gender information for anaphora resolution[C]//Proceedings of the Canadian Conference on Artificial Intelligence,2005:342-353.
    [65]Xiaofeng Yang,Jian Su.Coreference resolution using semantic relatedness information from automatically discovered patterns[C]//Proceedings of the Annual Meeting of the Association for Computational Linguistics(ACL),2007.
    [66]A.Rahman,V.Ng.Coreference resolution with world knowledge[C]//Proceedings of the Annual Meeting of the Association for Computational Linguistics(ACL),2011:814-824.
    [67]M.Poesio,R.Mehta,A.Maroudas,et al.Learning to resolve bridging references[C]//Proceedings of the Annual Meeting of the Association for Computational Linguistics(ACL),2004:143-150.
    [68]Heng Ji,Ralph Grishman.Knowledge base population:Successful approaches and challenges[C]//Proceedings of the Annual Meeting of the Association for Computational Linguistics(ACL),2011:1148-1158.
    [69]S.Singh,A.Subramanya,F.Pereira,et al.Largescale cross-document coreference using distributed inference and hierarchical models[C]//Proceedings of the Annual Meeting of the Association for Computational Linguistics(ACL),2011.
    [70]C.A.Bejan,M.Titsworth,A.Hickl,et al.Nonparametric bayesian models for unsupervised event coreference resolution[C]//Proceedings of Neural Information Processing Systems(NIPS),2009:73-81.
    [71]Zheng Chen,Heng Ji.Graph-based event coreference resolution[C]//Proceedings of the Annual Meeting of the Association for Computational Linguistics(ACL),2009:54-57.

© 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