中文指代消解模型的对比研究

doi:10.11896/j.issn.1002-137X.2016.02.006

摘要/Abstract

摘要： 指代消解的基本任务是把指向现实世界中相同实体的所有实体表达关联起来。与英文指代消解的研究相比,中文指代消解的研究相对较少,至今没有对现存的中文指代消解模型进行公平的测评和比较,主要原因是现存的中文指代消解模型在训练和测评时采用了不同的语料,且所选用的特征属性也不相同。基于上述原因,实现了5类基本的中文指代消解模型,并在ACE2005中文语料上进行同平台、同语料、同特征的测评。通过测评比较了各类模型的性能,同时分析和探讨了影响中文指代消解模型精度的各种因素。

关键词: 人工智能,指代消解模型,指代消解,自然语言处理

Abstract: The task of anaphora resolution is determining linguistic expressions that refer to the same real-world entity in a text.Compared to the amount of research on English anaphora resolution,relatively little work has been done on Chinese anaphora resolution.To our best knowleage,there is no fair comparison on the Chinese anaphora resolution models,mainly because of the useage of different data and features.We aimed to gain insights into the factors that affect the performance of the models and the advantages of each model via experiment with the same data and features in the ACE2005 Chinese corpus.

Key words: Artificial intelligence,Anaphora resolution models,Anaphora resolution,Natural language processing

周炫余,刘娟,罗飞,刘洋,颜晗. 中文指代消解模型的对比研究[J]. 计算机科学, 2016, 43(2): 31-34. https://doi.org/10.11896/j.issn.1002-137X.2016.02.006

ZHOU Xuan-yu, LIU Juan, LUO Fei, LIU Yang and YAN Han. Comparison of Chinese Anaphora Resolution Models[J]. Computer Science, 2016, 43(2): 31-34. https://doi.org/10.11896/j.issn.1002-137X.2016.02.006

参考文献

[1] Hardmeier C,Federico M.Modelling prono minal anaphora in statistical machine translation[C]∥Proceedings of the International Workshop on Spoken Language Translation.Paris:Konferensbidrag,2010:283-289
[2] Doddington G,Mitchell A,Przybocki M.The automatic content extraction (ACE) program-tasks,data,and evaluation[DB/OL].2012-05-11.http://www.comp.nus.edu.sg/rpnlpir/proceedings/lrec-2004/pdf/.pdf,2012
[3] Witte R,Krestel R,Bergler S.Context based multidocumentsummarization using fuzzy coreference cluster graphs [DB/OL].2012-05-06.http://www.nlpir.nist.gov/projects/duc/pubs/2006.papers/20.final.pdf,2012
[4] Wang Hou-feng,He Ting-ting.Research on Chinese Pronominal Anaphora Resolution[J].Chinese Journal of Computes,2001,4(2):136-143(in Chinese) 王厚峰,何婷婷.汉语中人称代词的消解研究[J].计算机学报,2001,24(2):136-143
[5] Wang Hou-feng,Mei Zheng.Robust Pronominal Resolutionwithin Chinese Text[J].Journal of Software,2005,6(5):700-707(in Chinese) 王厚峰,梅铮.鲁棒性的汉语人称代词消解[J].软件学报,2005,16(5):700-707
[6] Cardie C,Wagstaff K.Noun phrase coreference as clustering[C]∥Proceedings of the 1999 Joint SIGDAT Conference on Empirical Methods in Natural Language Processing and Very Large Corpora.College park:Kluwer Academic Publishers,1999:281-289
[7] Zhou Jun-sheng,Huang Shu-jian,Chen Jia-jun,et al.A NewGraph Clustering Algorithm for Chinese Noun Phrase Corefe-rence Resolution[J].Journal of Chinese Information Processing,2007,1(2):77-82(in Chinese) 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,2007,1(2):77-82
[8] Soon W M,Ng H T,Lim D C Y.A machine learning approach to coreference resolution of noun phrases[J].Computational Linguistics,2001,7(4):521-544
[9] Yang X Q,Su J,Zhou G D,et al.An NP-cluster based approach to coreference resolution[C]∥Proceedings of the 20th international conference on Computational Linguistics.Morristown:ACL,2004:226-232
[10] Denis P,Baldridge J.A Ranking Approach to Pronoun Resolution[C]∥International Joint Conferences on Artificial Intelligence.Hyderabad:ACL,2007:1588-1593
[11] Rahman A,Ng V.Narrowing the modeling gap:a cluster-ran-king approach to coreference resolution [J].Journal of Artificial Intelligence Research,2011,40(1):469-521
[12] Kong Fang,Zhu Qiao-ming,Zhou Guo-dong,et al.Coreference Resolution Based on Center Theory[J].Computer Science,2009,6(6):219-222(in Chinese) 孔芳,朱巧明,周国栋,等.基于中心理论的指代消解研究[J].计算机科学,2009,6(6):219-222
[13] Gao Jun-wei,Kong Fang,Zhu Qiao-ming,et al.Research of Chinese Noun Phrase Anaphora Resolution:A SVM-based Approach[J].Computer Science,2012,39(10):231-234(in Chinese) 高俊伟,孔芳,朱巧明,等.基于SVM 的中文名词短语指代消解研究[J].计算机科学,2012,39(10):231-234
[14] Kong Fang,Zhou Guo-dong.Pronoun Resolution in English and Chinese Languages Based on Tree Kernel[J].Journal of Software,2012,3(5):1085-1099(in Chinese) 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
[15] Xi Xue-feng,Zhou Guo-dong.Pronoun Resolution Based onDeep Learning[J].Acta Scientiarum Naturalium Universitatis Pekinensis,2014,50(1):100-110(in Chinese) 奚雪峰,周国栋.基于Deep Learning的代词指代消解[J].北京大学学报(自然科学版),2014,50(1):100-110
[16] Raghunathan K,Lee H,Rangarajan S.A multipass sieve forcoreference resolution [M].MIT,Massa chusetts:ACL,2010:492-501
[17] Lee H,Peirsman Y,Chang A,et al.Stanford’s multi-pass sieve coreference resolution system at the CoNLL-2011 shared task[C]∥Proceedings of the Fifteenth Conference on Computational Natural Language Learning:Shared Task.Oregon:ACL,2011:28-34
[18] Lee H,Chang A,Peirsman Y,et al.Deterministic coreference resolution based on entity-centric,precision-ranked rules[J].Computational Linguistics,2013,39(4):885-916
[19] Zhang X C,Wu H.Chinese coreference resolution via orderedfiltering[C]∥Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning:Shared Task.Jeju:ACL,2012:95-99
[20] Kong Fang,Zhu Qiao-ming,Zhou Guo-dong,et al.Anaphoricity Determination for Coreference Resolution in English and Chinese[J].Journal of Computer Research and Development,2012,49(5):1072-1085(in Chinese) 孔芳,朱巧明,周国栋,等.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,2012,9(5):1072-1085
[21] Marc V,John B,John A,et al.A model theoretic coreference scoring scheme[C]∥Proceedings of the 6th Message Understanding Conference.Stroudsburg:ACL,1995:45-52
[22] Amit B,Breck B.Algorithms for scoring coreference chains[C]∥Proceedings of LREC.Granada:ACL,1998:563-566
[23] Luo X Q.On coreference resolution performance metrics[C]∥Proceedings of HLT-EMNLP Stroudsburg.ACL,2005:25-32
[24] Nong Y.The Handbook of Data Mining[M].Cleveland CRCPress,2001:247-277
[25] Marta R,Eduard H.BLANC:Implementing the Rand Index for coreference evaluation[J].Natural Language Engineering,2011,17(4):485-510
[26] Doddington G,Mitchell A,Przybocki M.The automatic content extraction (ACE) program-tasks,data,and evaluation [DB/OL].2012-5-11.http:// www.comp.nus.edu.sg/~rpnlpir/ proceedings/ lrec-2004 /pdf/ 5.pdf

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed