面向细粒度隐式篇章关系识别的远距离监督特征学习算法
|
摘要
针对中文细粒度隐式篇章关系识别进行研究。考虑细粒度篇章关系的方向性特点,提出一种基于远距离监督的特征学习算法。该算法使用远距离监督的方法,自动标注显式篇章数据,然后利用词与连词之间的相对位置信息,训练各个词的词表达,将词的修辞功能以及关系的方向性编码到密集词表达中,将这样的词表达应用到细粒度隐式篇章关系分类器。实验结果表明,在细粒度隐式篇章关系识别任务中,该方法的分类准确率达到49.79%,比未考虑篇章关系方向性的方法有较大程度的提高。
Aiming at the identification of Chinese fine-grained implicit discourse relation and taking the directionality characteristic in account, the authors propose a feature learning algorithm based on the distant supervision to label explicit discourse data automatically. The relative position information between conjunction and words are applied to train the intensive word representation. Then the rhetorical function of words and the directionality of relations are encoded into the representation of intensive words, which is applied to the relation classification of fine-grained implicit discourses. From the experimental studies of the proposed approach, the classification accuracy reaches 49.79%, which are better than those approaches neglecting the directionality of discourse relations.
Aiming at the identification of Chinese fine-grained implicit discourse relation and taking the directionality characteristic in account, the authors propose a feature learning algorithm based on the distant supervision to label explicit discourse data automatically. The relative position information between conjunction and words are applied to train the intensive word representation. Then the rhetorical function of words and the directionality of relations are encoded into the representation of intensive words, which is applied to the relation classification of fine-grained implicit discourses. From the experimental studies of the proposed approach, the classification accuracy reaches 49.79%, which are better than those approaches neglecting the directionality of discourse relations.
引文
[1]Sun M,Chai J Y.Discourse processing for context question answering based on linguistic knowledge.Knowledge-Based Systems,2007,20(6):511-526
[2]Yoshida Y,Suzuki J,Hirao T,et al.Dependencybased discourse parser for single-document Summarization//Conference on Empirical Methods in Natural Language Processing.Doha,2014:1834-1839
[3]Li J J,Carpuat M,Nenkova A.Assessing the discourse factors that influence the quality of machine translation//Meeting of the Association for Computational Linguistics.Baltimore,2014:283-288
[4]Zhou Y,Xue N.PDTB-style discourse annotation of Chinese text//Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics:Long Papers-Volume 1.Jeju:Association for Computational Linguistics,2012:69-77
[5]Braud C,Denis P.Learning connective-based word representations for implicit discourse relation identification//Empirical Methods on Natural Language Processing.Austin,2016:203-213
[6]张牧宇,秦兵,刘挺.中文篇章级句间语义关系体系及标注.中文信息学报,2014,28(2):28-36
[7]Lin Z,Kan M Y,Ng H T.Recognizing implicit discourse relations in the Penn Discourse Treebank//Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing:Volume 1-Volume 1.Singapore:Association for Computational Linguistics,2009:343-351
[8]Ji Y,Eisenstein J.One vector is not enough:Entityaugmented distributional semantics for discourse relations[EB/OL].(2014-11-25)[2018-01-20].https://arxiv.org/pdf/1411.6699.pdf
[9]Rutherford A,Demberg V,Xue N.A Systematic study of neural discourse models for implicit discourse relation//Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics:Volume 1,Long Papers.Valencia,2017:281-291
[10]Wang J,Lan M.Two end-to-end shallow discourse parsers for English and Chinese in CoNLL-2016 shared task//Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics.Berlin,2016:33-40
[11]Schenk N,Chiarcos C,Donandt K,et al.Do we really need all those rich linguistic features?a neural network-based approach to implicit sense labeling//Proceedings of the CoNLL-16 shared task.Berlin,2016:41-49
[12]R?nnqvist S,Schenk N,Chiarcos C.A Recurrent neural model with attention for the recognition of Chinese implicit discourse relations//Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics.Vancouver,2017:256-262
[13]Sporleder C,Lascarides A.Using automatically labelled examples to classify rhetorical relations:an assessment.Natural Language Engineering,2008,14(3):369-416
[14]Qin L,Zhang Z,Zhao H.A stacking gated neural architecture for implicit discourse relation classification//Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing.Austin,2016:2263-2270
[15]Angeli G,Premkumar M J J,Manning C D.Leveraging linguistic structure for open domain information extraction//Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing(Volume 1:Long Papers).Beijing,2015:344-354
[16]Magdy W,Sajjad H,El-Ganainy T,et al.Distant supervision for tweet classification using youtube labels//ICWSM.Oxford,2015:638-641
[17]Marcu D.The rhetorical parsing of unrestricted texts:A surface-based approach.Computational linguistics,2000,26(3):395-448
[18]姬建辉,张牧宇,秦兵,等.中文篇章级句间关系自动分析.江西师范大学学报(自然科学版),2015,39(2):124-131
[19]Xue N,Ng H T,Pradhan S,et al.The conll-2015shared task on shallow discourse parsing//Proceedings of the Nineteenth Conference on Computational Natural Language Learning-Shared Task.Beijing,2015:1-16
[20]Hooda S,Kosseim L.Argument labeling of explicit discourse relations using LSTM neural networks[EB/OL].(2017-08-11)[2018-02-01].https://arxiv.org/pdf/1708.03425.pdf
[21]Wu C,Shi X,Chen Y,et al.Improving implicit discourse relation recognition with discourse-specific word embeddings//Meeting of the Association for Computational Linguistics.Vanvouver,2017:269-274
[22]Turney P D,Pantel P.From frequency to meaning:vector space models of semantics.Journal of Artificial Intelligence Research,2010,37:141-188
[23]Pitler E,Louis A,Nenkova A.Automatic sense prediction for implicit discourse relations in text//Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP.Singapore:Association for Computational Linguistics,2009:683-691
[2]Yoshida Y,Suzuki J,Hirao T,et al.Dependencybased discourse parser for single-document Summarization//Conference on Empirical Methods in Natural Language Processing.Doha,2014:1834-1839
[3]Li J J,Carpuat M,Nenkova A.Assessing the discourse factors that influence the quality of machine translation//Meeting of the Association for Computational Linguistics.Baltimore,2014:283-288
[4]Zhou Y,Xue N.PDTB-style discourse annotation of Chinese text//Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics:Long Papers-Volume 1.Jeju:Association for Computational Linguistics,2012:69-77
[5]Braud C,Denis P.Learning connective-based word representations for implicit discourse relation identification//Empirical Methods on Natural Language Processing.Austin,2016:203-213
[6]张牧宇,秦兵,刘挺.中文篇章级句间语义关系体系及标注.中文信息学报,2014,28(2):28-36
[7]Lin Z,Kan M Y,Ng H T.Recognizing implicit discourse relations in the Penn Discourse Treebank//Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing:Volume 1-Volume 1.Singapore:Association for Computational Linguistics,2009:343-351
[8]Ji Y,Eisenstein J.One vector is not enough:Entityaugmented distributional semantics for discourse relations[EB/OL].(2014-11-25)[2018-01-20].https://arxiv.org/pdf/1411.6699.pdf
[9]Rutherford A,Demberg V,Xue N.A Systematic study of neural discourse models for implicit discourse relation//Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics:Volume 1,Long Papers.Valencia,2017:281-291
[10]Wang J,Lan M.Two end-to-end shallow discourse parsers for English and Chinese in CoNLL-2016 shared task//Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics.Berlin,2016:33-40
[11]Schenk N,Chiarcos C,Donandt K,et al.Do we really need all those rich linguistic features?a neural network-based approach to implicit sense labeling//Proceedings of the CoNLL-16 shared task.Berlin,2016:41-49
[12]R?nnqvist S,Schenk N,Chiarcos C.A Recurrent neural model with attention for the recognition of Chinese implicit discourse relations//Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics.Vancouver,2017:256-262
[13]Sporleder C,Lascarides A.Using automatically labelled examples to classify rhetorical relations:an assessment.Natural Language Engineering,2008,14(3):369-416
[14]Qin L,Zhang Z,Zhao H.A stacking gated neural architecture for implicit discourse relation classification//Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing.Austin,2016:2263-2270
[15]Angeli G,Premkumar M J J,Manning C D.Leveraging linguistic structure for open domain information extraction//Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing(Volume 1:Long Papers).Beijing,2015:344-354
[16]Magdy W,Sajjad H,El-Ganainy T,et al.Distant supervision for tweet classification using youtube labels//ICWSM.Oxford,2015:638-641
[17]Marcu D.The rhetorical parsing of unrestricted texts:A surface-based approach.Computational linguistics,2000,26(3):395-448
[18]姬建辉,张牧宇,秦兵,等.中文篇章级句间关系自动分析.江西师范大学学报(自然科学版),2015,39(2):124-131
[19]Xue N,Ng H T,Pradhan S,et al.The conll-2015shared task on shallow discourse parsing//Proceedings of the Nineteenth Conference on Computational Natural Language Learning-Shared Task.Beijing,2015:1-16
[20]Hooda S,Kosseim L.Argument labeling of explicit discourse relations using LSTM neural networks[EB/OL].(2017-08-11)[2018-02-01].https://arxiv.org/pdf/1708.03425.pdf
[21]Wu C,Shi X,Chen Y,et al.Improving implicit discourse relation recognition with discourse-specific word embeddings//Meeting of the Association for Computational Linguistics.Vanvouver,2017:269-274
[22]Turney P D,Pantel P.From frequency to meaning:vector space models of semantics.Journal of Artificial Intelligence Research,2010,37:141-188
[23]Pitler E,Louis A,Nenkova A.Automatic sense prediction for implicit discourse relations in text//Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP.Singapore:Association for Computational Linguistics,2009:683-691
© 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 |