{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T14:48:29Z","timestamp":1753886909602,"version":"3.41.2"},"reference-count":24,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2018,7,3]],"date-time":"2018-07-03T00:00:00Z","timestamp":1530576000000},"content-version":"vor","delay-in-days":183,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61772324","61673248"],"award-info":[{"award-number":["61772324","61673248"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004480","name":"Natural Science Foundation of Shanxi Province","doi-asserted-by":"publisher","award":["201601D102030"],"award-info":[{"award-number":["201601D102030"]}],"id":[{"id":"10.13039\/501100004480","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Wireless Communications and Mobile Computing"],"published-print":{"date-parts":[[2018,1]]},"abstract":"<jats:p>Comprehending unstructured text is a challenging task for machines because it involves understanding texts and answering questions. In this paper, we study the multiple\u2010choice task for reading comprehension based on MC Test datasets and Chinese reading comprehension datasets, among which Chinese reading comprehension datasets which are built by ourselves. Observing the above\u2010mentioned training sets, we find that \u201csentence comprehension\u201d is more important than \u201cword comprehension\u201d in multiple\u2010choice task, and therefore we propose sentence\u2010level neural network models. Our model firstly uses LSTM network and a composition model to learn compositional vector representation for sentences and then trains a sentence\u2010level attention model for obtaining the sentence\u2010level attention between the sentence embedding in documents and the optional sentences embedding by dot product. Finally, a consensus attention is gained by merging individual attention with the merging function. Experimental results show that our model outperforms various state\u2010of\u2010the\u2010art baselines significantly for both the multiple\u2010choice reading comprehension datasets.<\/jats:p>","DOI":"10.1155\/2018\/2678976","type":"journal-article","created":{"date-parts":[[2018,7,3]],"date-time":"2018-07-03T23:38:44Z","timestamp":1530661124000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Using Sentence\u2010Level Neural Network Models for Multiple\u2010Choice Reading Comprehension Tasks"],"prefix":"10.1155","volume":"2018","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4816-7304","authenticated-orcid":false,"given":"Yuanlong","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ru","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongyan","family":"Tan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qinghua","family":"Chai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2018,7,3]]},"reference":[{"key":"e_1_2_10_1_2","doi-asserted-by":"crossref","unstructured":"ChenD. BoltonJ. andManningC. D. A thorough examination of the CNN\/daily mail reading comprehension task Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics ACL 2016 August 2016 2358\u20132367 2-s2.0-85012005003.","DOI":"10.18653\/v1\/P16-1223"},{"key":"e_1_2_10_2_2","first-page":"247","article-title":"Knowledge representation learning: a review","volume":"53","author":"Liu Y. Z.","year":"2016","journal-title":"Journal of Computer Research and Development"},{"key":"e_1_2_10_3_2","doi-asserted-by":"crossref","unstructured":"MatthewR. ChristopherJ. C. andErinR. MCTest: a challenge dataset for the open-domain machine comprehension of text Proceedings of the 2013 on Empirical Methods in Natural Language Processing 2013 193\u2013203.","DOI":"10.18653\/v1\/D13-1020"},{"key":"e_1_2_10_4_2","unstructured":"FelixH. AntoineB. SumitC. andJasonW. The goldilocks principle: reading children s books with explicit memory representations 2015 https:\/\/arxiv.org\/abs\/1511.02301."},{"key":"e_1_2_10_5_2","unstructured":"PranavR. JianZ. KonstantinL. andPercyL. SQuAD: 100 000+ Questions for machine comprehension of text Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing 2016 2383\u20132392."},{"key":"e_1_2_10_6_2","unstructured":"MandarJ. EunsolC. DanielSW. andLukeZ. TriviaQA: a large scale distantly supervised challenge dataset for reading comprehension Proceeding of the 55th Annual Meeting of the Association for Computational Linguistics 2017 1601\u20131611."},{"key":"e_1_2_10_7_2","unstructured":"CuiY. M. LiuT. andChenZ. P. Consensus attention- based neural networks for Chinese reading comprehension 2016 https:\/\/arxiv.org\/help\/prep."},{"key":"e_1_2_10_8_2","doi-asserted-by":"crossref","unstructured":"CuiY. ChenZ. WeiS. WangS. LiuT. andHuG. Attention-over-attention neural networks for reading comprehension Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics 2017 593\u2013602.","DOI":"10.18653\/v1\/P17-1055"},{"key":"e_1_2_10_9_2","first-page":"1684","article-title":"Teaching machines to read and comprehend","author":"Karl M. H.","year":"2015","journal-title":"In Advances in Neural Information Processing Systems"},{"key":"e_1_2_10_10_2","doi-asserted-by":"crossref","unstructured":"Karl PRaymondJ. M. Using sentence-level LSTM language models for script inference Proceeding of the 54th Annual Meeting of the Association for Computational Linguistics 2016 279\u2013289.","DOI":"10.18653\/v1\/P16-1027"},{"key":"e_1_2_10_11_2","doi-asserted-by":"crossref","unstructured":"MrinmayaS. AvinavaD. EricP. X. andMatthewR. Learning answer-entailing structures for machine comprehension In Proceeding of the 53th Annual Meeting of the Association for Computational Linguistics 2015 239\u2013249.","DOI":"10.3115\/v1\/P15-1024"},{"key":"e_1_2_10_12_2","doi-asserted-by":"crossref","unstructured":"WangH. MohitB. KevinG. andDavidA. M. Machine comprehension with syntax frames and semantics Proceedings of the 53th Annual Meeting of the Association for Computational Linguistics 2015 700\u2013706.","DOI":"10.3115\/v1\/P15-2115"},{"key":"e_1_2_10_13_2","doi-asserted-by":"crossref","unstructured":"AdamT. YeZ. andXingdiY. A parallel-hierarchical model for machine comprehension on sparse Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics 2016 432\u2013441.","DOI":"10.18653\/v1\/P16-1041"},{"key":"e_1_2_10_14_2","doi-asserted-by":"crossref","unstructured":"YinW. EbertS. andSch\u00fctzeH. Attention-Based Convolutional Neural Network for Machine Comprehension Proceedings of the Workshop on Human-Computer Question Answering June 2016 San Diego California 15\u201321 https:\/\/doi.org\/10.18653\/v1\/W16-0103.","DOI":"10.18653\/v1\/W16-0103"},{"key":"e_1_2_10_15_2","unstructured":"RudolfK. MartinS. OndrejB. andJanK. Text understanding with the attention sum reader network 2016 https:\/\/arxiv.org\/abs\/1603.01547."},{"key":"e_1_2_10_16_2","unstructured":"BhuwanD. Liu XH. andYang ZL. Gated-attention readers for text comprehension Proceeding of the 55th Annual Meeting of the Association for Computational Linguistics 2017 1832\u20131846."},{"key":"e_1_2_10_17_2","first-page":"1741","article-title":"Sentence composition model for reading comprehension","volume":"37","author":"Wang Y. L.","year":"2017","journal-title":"Journal of Computer Application"},{"key":"e_1_2_10_18_2","unstructured":"MatthewD. Z. Adadelta: an adaptive learning rate method 2012 https:\/\/arxiv.org\/abs\/1212.5701."},{"key":"e_1_2_10_19_2","unstructured":"TomasM. KaiC. GregC. andJeffreyD. Efficient estimation of word representations in vector space Proceedings of the In Proceedings of workshop at ICLR 2013 1\u201312."},{"key":"e_1_2_10_20_2","first-page":"1929","article-title":"Dropout, a simple way to prevent neural networks from overfitting","volume":"15","author":"Nitish S.","year":"2014","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_2_10_21_2","unstructured":"Theano Development Team Theano: a python framework for fast computation of mathematical expressions 2016 https:\/\/arxiv.org\/abs\/1605.02688."},{"key":"e_1_2_10_22_2","unstructured":"BaolinP. ZhengdongL. HangL. andKanfaiW. Toward neural network-based reasoning 2015 https:\/\/arxiv.org\/abs\/1508.05508."},{"key":"e_1_2_10_23_2","first-page":"80","article-title":"Answer sentence extraction of reading comprehension based on shallow sematic tree kernel","volume":"22","author":"Zhang Z. C.","year":"2008","journal-title":"Journal of Chinese Information Processing"},{"key":"e_1_2_10_24_2","unstructured":"KaishengT. RichardS. andChristopherD. M. Improved semantic representations from tree-structured long short-term memory networks Proceedings of the 53th Annual Meeting of the Association for Computational Linguistics 2015 1556\u20131566."}],"container-title":["Wireless Communications and Mobile Computing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/downloads.hindawi.com\/journals\/wcmc\/2018\/2678976.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/wcmc\/2018\/2678976.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/2018\/2678976","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,5]],"date-time":"2025-07-05T15:02:45Z","timestamp":1751727765000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1155\/2018\/2678976"}},"subtitle":[],"editor":[{"given":"Tianyong","family":"Hao","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2018,1]]},"references-count":24,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2018,1]]}},"alternative-id":["10.1155\/2018\/2678976"],"URL":"https:\/\/doi.org\/10.1155\/2018\/2678976","archive":["Portico"],"relation":{},"ISSN":["1530-8669","1530-8677"],"issn-type":[{"type":"print","value":"1530-8669"},{"type":"electronic","value":"1530-8677"}],"subject":[],"published":{"date-parts":[[2018,1]]},"assertion":[{"value":"2018-03-28","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2018-06-13","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2018-07-03","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"2678976"}}