{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T15:04:53Z","timestamp":1753887893797,"version":"3.41.2"},"reference-count":31,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2021,2,19]],"date-time":"2021-02-19T00:00:00Z","timestamp":1613692800000},"content-version":"vor","delay-in-days":49,"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":["61462002","61762003","61862001"],"award-info":[{"award-number":["61462002","61762003","61862001"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012490","name":"North Minzu University","doi-asserted-by":"publisher","award":["2018ZHJY01","ZDZX201801"],"award-info":[{"award-number":["2018ZHJY01","ZDZX201801"]}],"id":[{"id":"10.13039\/501100012490","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Computational Intelligence and Neuroscience"],"published-print":{"date-parts":[[2021,1]]},"abstract":"<jats:p>Text\u2010based multitype question answering is one of the research hotspots in the field of reading comprehension models. Multitype reading comprehension models have the characteristics of shorter time to propose, complex components of relevant corpus, and greater difficulty in model construction. There are relatively few research works in this field. Therefore, it is urgent to improve the model performance. In this paper, a text\u2010based multitype question and answer reading comprehension model (MTQA) is proposed. The model is based on a multilayer transformer encoding and decoding structure. In the decoding structure, the headers of the answer type prediction decoding, fragment decoding, arithmetic decoding, counting decoding, and negation are added for the characteristics of multiple types of corpora. Meanwhile, high\u2010performance ELECTRA checkpoints are employed, and secondary pretraining based on these checkpoints and an absolute loss function are designed to improve the model performance. The experimental results show that the performance of the proposed model on the DROP and QUOREF corpora is better than the best results of the current existing models, which proves that the proposed MTQA model has high feature extraction and relatively strong generalization capabilities.<\/jats:p>","DOI":"10.1155\/2021\/8810366","type":"journal-article","created":{"date-parts":[[2021,2,20]],"date-time":"2021-02-20T00:54:57Z","timestamp":1613782497000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["MTQA: Text\u2010Based Multitype Question and Answer Reading Comprehension Model"],"prefix":"10.1155","volume":"2021","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7801-008X","authenticated-orcid":false,"given":"Deguang","family":"Chen","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6764-6135","authenticated-orcid":false,"given":"Ziping","family":"Ma","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4122-2895","authenticated-orcid":false,"given":"Lin","family":"Wei","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1291-286X","authenticated-orcid":false,"given":"Jinlin","family":"Ma","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4752-1079","authenticated-orcid":false,"given":"Yanbin","family":"Zhu","sequence":"additional","affiliation":[]}],"member":"311","published-online":{"date-parts":[[2021,2,19]]},"reference":[{"key":"e_1_2_9_1_2","doi-asserted-by":"crossref","unstructured":"XueW.andLiT. Aspect based sentiment analysis with gated convolutional networks Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics July 2018 Melbourne Australia.","DOI":"10.18653\/v1\/P18-1234"},{"key":"e_1_2_9_2_2","doi-asserted-by":"crossref","unstructured":"HuM.andLiuB. Mining and summarizing customer reviews Proceedings of the 2004 ACM SIGKDD International Conference on Knowledge Discovery and Data Mining\u2014KDD\u201804 August 2004 Seattle WA USA 168\u2013177 https:\/\/doi.org\/10.1145\/1014052.1014073.","DOI":"10.1145\/1014052.1014073"},{"key":"e_1_2_9_3_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.293"},{"key":"e_1_2_9_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2946594"},{"key":"e_1_2_9_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3016727"},{"key":"e_1_2_9_6_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.448"},{"key":"e_1_2_9_7_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.320"},{"key":"e_1_2_9_8_2","doi-asserted-by":"crossref","unstructured":"NiuX. MathurP. DinuG. andOnaizanY. A. Evaluating robustness to input perturbations for neural machine translation 2020 https:\/\/arxiv.org\/abs\/2005.00580.","DOI":"10.18653\/v1\/2020.acl-main.755"},{"key":"e_1_2_9_9_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.412"},{"key":"e_1_2_9_10_2","doi-asserted-by":"crossref","unstructured":"ZhengB. WenH. LiangY.et al. Document modeling with graph attention networks for multi-grained machine reading comprehension 2020 https:\/\/arxiv.org\/abs\/2005.05806.","DOI":"10.18653\/v1\/2020.acl-main.599"},{"key":"e_1_2_9_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3004002"},{"key":"e_1_2_9_12_2","doi-asserted-by":"crossref","unstructured":"JoshiM. ChoiE. WeldD. S. andZettlemoyerL. TriviaQA: a large scale distantly supervised challenge dataset for reading comprehension \u201d in association for computational linguistics (acl) vancouver Canada 2017 https:\/\/arxiv.org\/abs\/1705.03551.","DOI":"10.18653\/v1\/P17-1147"},{"key":"e_1_2_9_13_2","doi-asserted-by":"crossref","unstructured":"RajpurkarP. ZhangJ. LopyrevK. andLiangP. SQuAD: 100 000+ questions for machine comprehension of text Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing 2016 November 2016 Austin TX USA.","DOI":"10.18653\/v1\/D16-1264"},{"key":"e_1_2_9_14_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-2124"},{"key":"e_1_2_9_15_2","unstructured":"DunnM. SagunL. HigginsM.et al. A new Q&A dataset augmented with context from a search engine 2017 https:\/\/arxiv.org\/abs\/1704.05179."},{"key":"e_1_2_9_16_2","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00023"},{"key":"e_1_2_9_17_2","unstructured":"HermannK. M. Ko\u010disk\u00fdT. GrefenstetteE.et al. Teaching machines to read and comprehend 2015 https:\/\/arxiv.org\/abs\/1506.03340."},{"key":"e_1_2_9_18_2","doi-asserted-by":"crossref","unstructured":"DuaD. WangY. DasigiP. StanovskyG. SinghS. andGardnerM. Quoref: a reading comprehension dataset with questions requiring coreferential reasoning Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) December 2019 Hong Kong China https:\/\/doi.org\/10.18653\/v1\/d19-1606.","DOI":"10.18653\/v1\/D19-1606"},{"key":"e_1_2_9_19_2","doi-asserted-by":"crossref","unstructured":"The Association for Computational Linguistics DROP: A reading comprehension benchmark requiring Discrete reasoning over paragraphs Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics 2019 Minneapolis MN USA 2368\u20132378 https:\/\/doi.org\/10.18653\/v1\/N19-1246.","DOI":"10.18653\/v1\/N19-1246"},{"key":"e_1_2_9_20_2","doi-asserted-by":"crossref","unstructured":"RanQ. LinY. LiP. ZhouJ. andLiuZ. NumNet: machine reading comprehension with numerical reasoning 2019 https:\/\/arxiv.org\/abs\/1910.06701.","DOI":"10.18653\/v1\/D19-1251"},{"key":"e_1_2_9_21_2","doi-asserted-by":"crossref","unstructured":"HuM. PengY. HuangZ. andLiD. A multi-type multi-span network for reading comprehension that requires discrete reasoning 2019 https:\/\/arxiv.org\/abs\/1908.05514.","DOI":"10.18653\/v1\/D19-1170"},{"key":"e_1_2_9_22_2","unstructured":"EfratA. SegalE. andShohamM. Tag-based multi-span extraction in reading comprehension 2019 https:\/\/arxiv.org\/abs\/1909.13375."},{"key":"e_1_2_9_23_2","doi-asserted-by":"crossref","unstructured":"GevaM. GuptaA. andBerantJ. Injecting numerical reasoning skills into language models 2020 https:\/\/arxiv.org\/abs\/2004.04487.","DOI":"10.18653\/v1\/2020.acl-main.89"},{"key":"e_1_2_9_24_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.740"},{"key":"e_1_2_9_25_2","unstructured":"GoodfellowI. J. AbadieJ. P. MirzaM.et al. Generative adversarial nets Proceedings of the Advances in Neural Information Processing Systems 2014 London UK 2672\u20132680."},{"key":"e_1_2_9_26_2","unstructured":"SegalE. EfratA. ShohamM. GlobersonA. andBerantJ. A simple and effective model for answering multi-span questions 2019 https:\/\/arxiv.org\/abs\/1909.13375."},{"key":"e_1_2_9_27_2","unstructured":"YuA. W. DohanD. LuongM. T.et al. Fast and accurate reading comprehension by combining self-attention and convolution Proceedings of the 12th International Conference on Artificial Neural Networks 2018."},{"key":"e_1_2_9_28_2","unstructured":"DevlinJ. ChangM. W. LeeK. andToutanovaK. BERT: pre-training of deep bidirectional transformers for language understanding 2018 https:\/\/arxiv.org\/abs\/1810.04805."},{"key":"e_1_2_9_29_2","unstructured":"ClarkK. LuongM. T. LeQ. V. andManningC. D. ELECTRA: Pre-training text encoders as discriminators rather than generators Proceedings of the International Conference on Learning Representations May 2020 Scottsdale AZ USA."},{"key":"e_1_2_9_30_2","unstructured":"YuA. W. DohanD. LuongM. T.et al. QANet: combining local convolution with global self-attention for reading comprehension Proceedings of the International Conference on Learning Representations May 2018 Vancouver Canada."},{"key":"e_1_2_9_31_2","doi-asserted-by":"crossref","unstructured":"YeD. LinY. DuJ. LiuZ. SunM. andLiuZ. Coreferential reasoning learning for language representation 2020 https:\/\/arxiv.org\/abs\/2004.%2006870.","DOI":"10.18653\/v1\/2020.emnlp-main.582"}],"container-title":["Computational Intelligence and Neuroscience"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/downloads.hindawi.com\/journals\/cin\/2021\/8810366.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/cin\/2021\/8810366.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/2021\/8810366","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,6]],"date-time":"2024-08-06T12:22:34Z","timestamp":1722946954000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1155\/2021\/8810366"}},"subtitle":[],"editor":[{"given":"Paolo","family":"Gastaldo","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2021,1]]},"references-count":31,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,1]]}},"alternative-id":["10.1155\/2021\/8810366"],"URL":"https:\/\/doi.org\/10.1155\/2021\/8810366","archive":["Portico"],"relation":{},"ISSN":["1687-5265","1687-5273"],"issn-type":[{"type":"print","value":"1687-5265"},{"type":"electronic","value":"1687-5273"}],"subject":[],"published":{"date-parts":[[2021,1]]},"assertion":[{"value":"2020-09-22","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-02-01","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-02-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"8810366"}}