End to End Chinese Coreference Resolution with Structural Information

doi:10.19678/j.issn.1000-3428.0053562

Abstract

Abstract: On the basis of the end to end coreference resolution model proposed by LEE et al.,this paper further considers the characteristics of Chinese writing and proposes a Chinese coreference resolution model with structural information.The constituency tree of all sentences is compressed to obtain the leaf node depth of the document compression tree.The Structural Embedding of Constituency Tree(SECT) is used to vectorize the structural information.The part of speech,the leaf node depth and the SECT information are introduced into the model as three eigenvectors for Chinese coreference resolution.The test results on the CoNLL2012 dataset show that the application of the three eigenvectors can effectively improve the Chinese coreference resolution of the proposed model,whose average F₁ value can reach 62.33%,which is 5.28% higher than the baseline.

Key words: end to end coreference resolution, structural embedding, part of speech, constituency tree, document syntactic compression tree

摘要： 在LEE等人提出的端到端指代消解模型基础上，考虑中文行文特点，提出一种融合结构化信息的中文指代消解模型。压缩文档中所进行有句子对应的成分句法树并获取文档压缩树叶节点深度，采用成分句法树的结构化嵌入（SECT）方法将结构信息进行向量化处理，将词性、文档压缩树叶节点深度与SECT信息作为3个特征向量引入模型中进行中文指代消解。在CoNLL2012数据集中的测试结果表明，通过结合上述3个特征，可使该模型的中文指代消解性能得到有效提高，其平均F₁值可达62.33%，较基准模型提升5.28%。

关键词: 端到端指代消解, 结构化嵌入, 词性, 成分句法树, 文档句法压缩树

CLC Number:

TP391

FU Jian, KONG Fang. End to End Chinese Coreference Resolution with Structural Information[J]. Computer Engineering, 2020, 46(1): 45-51.

付健, 孔芳. 融入结构化信息的端到端中文指代消解[J]. 计算机工程, 2020, 46(1): 45-51.

/ / Recommend / Download Citations

URL: http://www.ecice06.com/EN/10.19678/j.issn.1000-3428.0053562

http://www.ecice06.com/EN/Y2020/V46/I1/45

Figures/Tables 9

References

[1] VILAIN M,BURGER J,ABERDEEN J,et al.A model-theoretic coreference scoring scheme[C]//Proceedings of the 6th Conference on Message Understanding.New York,USA:ACM Press,1995:45-52.
[2] HIRSCHMAN L,ROBINSON P,BURGER J,et al.Automating coreference:the role of annotated training data[C]//Proceedings of AAAI Spring Symposium on Applying Machine Learning to Discourse Processing.Palo Alto,USA:AAAI,1997:118-121.
[3] DODDINGTON G R,MITCHELL A,PRZYBOCKI M A,et al.The Automatic Content Extraction(ACE) Program-tasks,data,and evaluation[C]//Proceedings of LREC'04.[S.l.]:ELRA,2004:1.
[4] PRADHAN S,RAMSHAW L,MARCUS M,et al.CoNLL-2011 shared task:modeling unrestricted coreference in OntoNotes[C]//Proceedings of the 15th Conference on Computational Natural Language Learning:Shared Task.New York,USA:ACM Press,2011:1-27.
[5] PRADHAN S,MOSCHITTI A,XUE Nianwen,et al.CoNLL-2012 shared task:modeling multilingual unrestricted coreference in OntoNotes[C]//Proceedings of Joint Conference on EMNLP and CoNLL-Shared Task.New York,USA:ACM Press,2012:1-40.
[6] NG V,CARDIE C.Improving machine learning approaches to coreference resolution[C]//Proceedings of the 40th Annual Meeting on Association for Computational Linguistics.Stroudsburg,USA:ACL Press,2002:104-111.
[7] ZHENG J,CHAPMAN W W,MILLER T A,et al.A system for coreference resolution for the clinical narrative[J].Journal of the American Medical Informatics Association,2012,19(4):660-667.
[8] WELLNER B,MCCALLUM A,PENG F,et al.An integrated,conditional model of information extraction and coreference with application to citation matching[C]//Proceedings of the 20th Conference on Uncertainty in Artificial Intelligence.New York,USA:ACM Press,2004:593-601.
[9] MIKOLOV T,SUTSKEVER I,CHEN K,et al.Distributed representations of words and phrases and their compositionality[C]//Proceedings of Advances in Neural Information Processing Systems.[S.l.]:Neural Information Processing Systems Foundation,Inc.,2013:3111-3119.
[10] PENNINGTON J,SOCHER R,MANNING C.GloVe:global vectors for word representation[C]//Proceedings of 2014 Conference on Empirical Methods in Natural Language Processing.Stroudsburg,USA:ACL Press,2014:1532-1543.
[11] WISEMAN S,RUSH A M,SHIEBER S,et al.Learning anaphoricity and antecedent ranking features for coreference resolution[C]//Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing.Stroudsburg,USA:ACL Press,2015:1416-1426.
[12] WISEMAN S,RUSH A M,SHIEBER S M.Learning global features for coreference resolution[C]//Proceedings of NAACL-HLT.New York,USA:ACM Press,2016:994-1004.
[13] CLARK K,MANNING C D.Deep reinforcement learning for mention-ranking coreference models[C]//Proceedings of 2016 Conference on Empirical Methods in Natural Language Processing.Stroudsburg,USA:ACL Press,2016:2256-2262.
[14] LEE K,HE L,LEWIS M,et al.End-to-end neural coreference resolution[C]//Proceedings of 2017 Conference on Empirical Methods in Natural Language Processing.Stroudsburg,USA:ACL Press,2017:188-197.
[15] XI Xuefeng,ZHOU Guodong.Pronoun resolution based on deep 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] LI Dongbai,TIAN Shengwei,YU Long,et al.Deep learning for pronominal anaphora resolution in Uyghur[J].Journal of Chinese Information Processing,2017,31(4):80-88.(in Chinese)李冬白,田生伟,禹龙,等.基于深度学习的维吾尔语人称代词指代消解[J].中文信息学报,2017,31(4):80-88.
[17] LI Min,YU Long,TIAN Shengwei,et al.Coreference re-solution of Uyghur noun phrases based on deep learning[J].Acta Automatica Sinica,2017,43(11):1984-1992.(in Chinese)李敏,禹龙,田生伟,等.基于深度学习的维吾尔语名词短语指代消解[J].自动化学报,2017,43(11):1984-1992.
[18] LIU Rui,HU Junjie,WEI Wei,et al.Structural embedding of syntactic trees for machine comprehension[C]//Proceedings of 2017 Conference on Empirical Methods in Natural Language Processing.Stroudsburg,USA:ACL Press,2017:815-824.
[19] AL-RFOU R,PEROZZI B,SKIENA S.Polyglot:distributed word representations for multilingual NLP[C]//Proceedings of the 17th Conference on Computational Natural Language Learning.Stroudsburg,USA:ACL Press,2013:183-192.
[20] LING W,DYER C,BLACK A W,et al.Finding function in form:compositional character models for open vocabulary word representation[C]//Proceedings of 2015 Conference on Empirical Methods in Natural Language Processing.Stroudsburg,USA:ACL Press,2015:1520-1530.
[21] SRIVASTAVA N,HINTON G,KRIZHEVSKY A,et al.Dropout:a simple way to prevent neural networks from overfitting[J].Journal of Machine Learning Research,2014,15(1):1929-1958.

Please choose a citation manager

Content to export