Multiple-to-One Chinese Textual Entailment for Reading Comprehension
CHEN Qian1, CHEN Xiafei1, GUO Xin1,2, WANG Suge1
1. School of Computer and Information Technology, Shanxi University, Taiyuan, Shanxi 030006, China; 2. School of Electronics and Information Engineering, Tongji University, Shanghai 201804, China
Abstract：As a kind of micro reading pattern, machine reading comprehension has attracted much attention in the field of automatic question-answering in recent years. The multiple-to-one textual entailment is a popular phenomenon in the machine reading comprehension. This paper first constructs M2OCTE corpus with 8000 multiple-to-one Chinese textual entailment pairs. Then it adopts a hierarchical neural network model, which can effectively integrate the semantic information between multiple sentences, to establish a unified expression for the multiple-to-one entailment pairs in an end-to-end style. The accuracy of the method on the university entrance exam of modern article reading comprehension entailment data set is 58.92%, which is higher than the traditional one-one entailment method. We also verify the effectiveness of the proposed method on an English data set.
[1] 任函, 盛雅琦, 冯文贺,等. 基于知识话题模型的文本蕴涵识别[J]. 中文信息学报, 2015, 29(6): 119-126. [2] 王宝鑫, 郑德权, 王晓雪, 等. 基于文本蕴含的选择类问题解答技术研究[J]. 北京大学学报 (自然科学版), 2016, 52(1): 134-140. [3] Kim M Y, Xu Y, Goebel R. Legal question answering using ranking svm and syntactic/semantic similarity[C]//Proceedings of the JSAI International Symposium on Artificial Intelligence. Berlin Heidelberg: Springer, 2014: 244-258. [4] Gómez-Adorno H, Pinto D, Vilarino D. A question answering system for reading comprehension tests[C]//Proceedings of the Mexican Conference on Pattern Recognition. Berlin Heidelberg: Springer, 2013: 354-363. [5] Sebastian, Galley M, Jurafsky D, et al. Textual entailment features for machine translation evaluation[C]//Proceedings of the Workshop on Statistical Machine Translation. Association for Computational Linguistics, 2009: 37-41. [6] Lloret E, Ferrández O, Munoz R, et al. A Text Summarization Approach under the Influence of Textual Entailment[C]//Proceedings of the 5th International Workshop on Natural Language Processing and Cognitive Science (NLPCS 2008). 2008: 22-31. [7] Wang R, Neumann G. Relation validation via textual entailment[C]//Proceedings of the Ontology-Based Information Extraction Systems (Obies 2008). 2008: 26-33. [8] Yin W, Ebert S, Schütze H. Attention-based convolutional neural network for machine comprehension[C]//The Workshop on Human-Computer Question Answering. 2016: 15-21. [9] Bowman S R, Angeli G, Potts C, et al. A large annotated corpus for learning natural language inference[C]//Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing. 2015: 632-642. [10] Shima H, Kanayama H, Lee C W, et al. Overview of NTCIR-9 RITE: Recognizing inference in text[C]//Proceeding of NTCIR-9 workshop meeting.Tokyo,2011: 291-301. [11] Dagan I, Glickman O. Probabilistic textual entailment: Generic applied modeling of language variability[C]//Proceedings of the PASCAL Workshop on Learning Methods for Text Understanding and Mining. Grenoble, France. 2004. [12] 张鹏, 李国臣, 李茹,等. 基于FrameNet框架关系的文本蕴含识别[J]. 中文信息学报, 2012, 26(2): 46-50. [13] 刘茂福, 李妍, 姬东鸿. 基于事件语义特征的中文文本蕴含识别[J]. 中文信息学报, 2013, 27(5): 129-136. [14] 张晗, 盛雅琦, 吕晨,等. 基于短文本隐含语义特征的文本蕴涵识别[J]. 中文信息学报, 2016, 30(3): 163-171. [15] 赵红燕, 刘鹏, 李茹, 王智强. 多特征文本蕴涵识别研究[J]. 中文信息学报, 2014, 28(2): 109-115. [16] Rocktschel T, Grefenstette E, Hermann K M, et al. Reasoning about entailment with neural attention[C]//Proceedings of the International Conference on Learning Representations. 2016. [17] Liu Y, Sun C, Lin L, et al. Learning natural language inferenceusing bidirectional LSTM model and Inner-Attention[J]. arXiv Preprint arXiv: 1605、09090.2016. [18] Li J, Luong T, Jurafsky D. A nierarchical neural autoencoder for paragraphs and documents[C]//Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing. 2015: 1106-1115. [19] Tang D, Qin B, Liu T. Document modeling with gated recurrent neural network for sentiment classification[C]//Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing. 2015: 1422-1432. [20] Lipton Z C, Berkowitz J, Elkan C. A critical review of recurrent neural networks for sequence learning[J]. arXiv preprint arXiv:2015,1506.00019. [21] 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: 3111-3119. [22] Mostafazadeh N, Roth M, Louis A, et al. LSDSem 2017 Shared Task: The story cloze test[C]//Proceedings of the Workshop on Linking MODELS of Lexical, Sentential and Discourse-Level Semantics. 2017: 46-51. [23] Le Q V, Mikolov T. Distributed representations of sentences and documents[J]. Computer Science, 2014, 4: 1188-1196. [24] Bowman S R, Gauthier J, Rastogi A, et al. A fast unified model for parsing and sentence understanding[C]//Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics. 2016: 1466-1477. [25] Mou L, Men R, Li G, et al. Natural language inference by tree-based convolution and heuristic matching[C]//Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics. 2016: 130-136.
2018, Vol. 32 
