孙凯丽,邓沌华,李源,李妙,李洋. 基于句内注意力机制多路CNN的汉语复句关系识别方法[J]. 中文信息学报, 2020, 34(6): 9-17,26.
SUN Kaili, DENG Dunhua, LI Yuan, LI Miao, LI Yang. Inner-Attention Based Multi-Way Convolutional Neural Network for Relation Recognition in Chinese Compound Sentence. , 2020, 34(6): 9-17,26.
Inner-Attention Based Multi-Way Convolutional Neural Network for Relation Recognition in Chinese Compound Sentence
SUN Kaili1, DENG Dunhua2, LI Yuan1, LI Miao1, LI Yang1
1.School of Computer Science, Central China Normal University, Wuhan, Hubei 430079, China; 2.Center for Research on Language and Language Education, Central China Normal University, Wuhan, Hubei 430079, China
Abstract：Compound sentence relation recognition is to identify for the semantic relation of clauses, which is the key task in semantic analysis of compound sentences. This task is difficult due to the an implicit relation in non-saturate compound sentences. To deal with the implicit semantic information, a multi-channel CNN based on the inner-attention mechanism is proposed in this paper. The inner-attention mechanism is based on Bi-LSTM, which enables it to learn bidirectional semantic features and associated features between clauses. At the same time, CNN is used to model the sentence representation to obtain local features. Compared with other results, experiment results on the CCCS and TCT show that the macro-F1 score and the average recall score of this paper reach 85.61% and 84.87%, achieving 6.08% and 3.05% relative improvement, respectively.
[1] Liu Y, Li S, Zhang X, et al. Implicit discourse relation classification via multi-task neural networks[C]//Proceedings of the 30th AAAI Conference on Artificial Intelligence, 2016. [2] Zou B, Zhou G, Zhu Q. Negation focus identification with contextual discourse information[C]//Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, 2014: 522-530. [3] Liakata M, Dobnik S, Saha S, et al. A discourse-driven content model for summarising scientific articles evaluated in a complex question answering task[C]//Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing,2013: 747-757. [4] Papineni K. BLEU: A method for automatic evaluation of machine translation[C]//Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics (ACL), 2002. [5] 吴锋文. 基于关系标记的汉语复句分类研究[J]. 汉语学报,2011(3): 63-73. [6] Schuster M, Paliwal K K. Bidirectional recurrent neural networks[J]. IEEE Transactions on Signal Processing, 1997, 45(11): 2673-2681. [7] Liu Y, Sun C, Lin L, et al. Learning natural language inference using bidirectional LSTM model and inner-attention[J]. arXiv preprint arXiv: 1605.09090, 2016. [8] Mou L, Men R, Li G, et al. Recognizing entailment and contradiction by tree-based convolution[J]. arXiv preprint arXiv: 1512.08422,2015. [9] 邢福义, 姚双云. 汉语复句语料库的建设与利用[C].HNC与语言学研究学术研讨会,2005. [10] 周强. 汉语句法树库标注体系[J]. 中文信息学报,2004,18(4): 2-9. [11] 邢福义.汉语复句研究[M]. 北京: 商务印书馆,2001: 1-37. [12] 黄伯荣,彦序东. 现代汉语: 下册. 北京: 高等教育出版社,2002. [13] 邵敬敏. 建立以语义特征为标志的汉语复句教学新系统刍议[J]. 世界汉语教学,2007(4): 94-104. [14] 李晋霞,刘云. 复句类型的演变[J]. 汉语学习,2007(2): 20-26. [15] 谢蓓. 对复句分类研究的回顾与思考[J]. 重庆科技学院学报(社会科学版),2006(6): 119-121. [16] 冯文贺. 汉语复句关系的特征结构[J]. 中文信息学报,2015,29(6): 13-22. [17] 胡金柱,吴锋文,李琼,等. 汉语复句关系词库的建设及其利用[J]. 语言科学, 2010(2): 133-142. [18] 胡金柱,舒江波,姚双云,等. 面向中文信息处理的复句关系词提取算法研究[J]. 计算机工程与科学,2009,31(10): 90-93. [19] 贾遂民, 雷利利, 胡明生. 基于规则的复句关系词的自动标识[J]. 中文信息学报, 2015, 29(1): 44-48. [20] 胡金柱,陈江曼,杨进才等. 基于规则的连用关系标记的自动标识研究[J]. 计算机科学,2012,39(7): 190-194. [21] 王东波,陈小荷,年洪东. 基于条件随机场的有标记联合结构自动识别[J]. 中文信息学报,2008, 22(6): 28-34. [22] 鲁松,宋柔. 汉英机器翻译中描述型复句的关系识别与处理[J]. 软件学报,2001,12(1): 83-93. [23] 周文翠,袁春风. 并列复句的自动识别初探[J].计算机应用研究,2008,25(3): 764-766. [24] 洪鹿平. 汉语复句关系自动判定研究[D]. 南京: 南京师范大学硕士学位论文,2008. [25] 李艳翠,孙静,周国栋等. 基于清华汉语树库的复句关系词识别与分类研究[J]. 北京大学学报(自然科学版),2014,50(1): 118-124. [26] 杨进才,陈忠忠,沈显君等. 二句式非充盈态有标复句关系类别的自动标志[J]. 计算机应用研究,2017(10): 76-79. [27] Kim Y. Convolutional neural networks for sentence classification[J]. arXiv preprint arXiv: 1408.5882,2014. [28] Rnnqvist S, Schenk N, Chiarcos C. A recurrent neural model with attention for the recognition of Chinese implicit discourse relations[J]. arXiv preprint arXiv: 1704.08092,2017. [29] 田文洪,高印权,黄厚文,等. 基于多任务双向长短时记忆网络的隐式句间关系分析[J].中文信息学报,2019,33(5): 47-53. [30] Mikolov T, Sutskever I, Chen K, et al. Distributed representations of words and phrases and their compositionality[C]//Proceedings of the Advances in Neural Information Processing Systems, 2013, 26: 3111-3119. [31] Pennington J, Socher R, Manning C. Glove: Global vectors for word representation[C]//Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP),2014: 1532-1543. [32] Rumelhart D E, Hinton G E, Williams R J. Learning internal representations by error propagation[G]//Allom C, Edward E.S. Cognitive Science, San Mnteo,CA: Morgan Kaufmann Publishers. 1986.[33] Paras. Stochastic Gradient Descent[CP/OL].[2019-07-30].https://www.math works.com/;matlabcentrol Hibee xcharge/4 347-stochnstic-gradtent-daescent.
2020, Vol. 34 
