{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T15:03:09Z","timestamp":1753887789000,"version":"3.41.2"},"reference-count":31,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2021,2,22]],"date-time":"2021-02-22T00:00:00Z","timestamp":1613952000000},"content-version":"vor","delay-in-days":52,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"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>Complex question answering in real world is a comprehensive and challenging task due to its demand for deeper question understanding and deeper inference. Information retrieval is a common solution and easy to implement, but it cannot answer questions which need long\u2010distance dependencies across multiple documents. Knowledge base (KB) organizes information as a graph, and KB\u2010based inference can employ logic formulas or knowledge embeddings to capture such long\u2010distance semantic associations. However, KB\u2010based inference has not been applied to real\u2010world question answering well, because there are gaps among natural language, complex semantic structure, and appropriate hypothesis for inference. We propose decoupling KB\u2010based inference by transforming a question into a high\u2010level triplet in the KB, which makes it possible to apply KB\u2010based inference methods to answer complex questions. In addition, we create a specialized question answering dataset only for inference, and our method is proved to be effective by conducting experiments on both AI2 Science Questions dataset and ours.<\/jats:p>","DOI":"10.1155\/2021\/6689740","type":"journal-article","created":{"date-parts":[[2021,2,22]],"date-time":"2021-02-22T23:50:07Z","timestamp":1614037807000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Taking a Closed\u2010Book Examination: Decoupling KB\u2010Based Inference by Virtual Hypothesis for Answering Real\u2010World Questions"],"prefix":"10.1155","volume":"2021","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3318-5318","authenticated-orcid":false,"given":"Xiao","family":"Zhang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0673-5019","authenticated-orcid":false,"given":"Guorui","family":"Zhao","sequence":"additional","affiliation":[]}],"member":"311","published-online":{"date-parts":[[2021,2,22]]},"reference":[{"key":"e_1_2_9_1_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-006-5833-1"},{"key":"e_1_2_9_2_2","unstructured":"JansenP. BalasubramanianN. SurdeanuM. andClarkP. What\u2019s in an explanation? characterizing knowledge and inference requirements for elementary science exams Proceedings of COLING 2016 the 26th International Conference on Computational Linguistics: Technical Papers December 2016 Osaka Japan The COLING 2016 Organizing Committee 2956\u20132965."},{"key":"e_1_2_9_3_2","doi-asserted-by":"publisher","DOI":"10.1016\/0743-1066(94)90035-3"},{"key":"e_1_2_9_4_2","unstructured":"LaoN. MitchellT. andCohenW. W. Random walk inference and learning in a large scale knowledge base Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing July 2011 Edinburgh UK Association for Computational Linguistics 529\u2013539."},{"key":"e_1_2_9_5_2","unstructured":"AntoineB. UsunierN. Garcia-DuranA. WestonJ. andYakhnenkoO. Translating embeddings for modeling multi-relational data Proceedings of the Advances in Neural Information Processing Systems (NIPS) December 2013 Lake Tahoe NV USA 2787\u20132795."},{"key":"e_1_2_9_6_2","unstructured":"NickelM. TrespV. andKriegelH.-P. A three-way model for collective learning on multi-relational data Proceedings of the 28th International Conference on Machine Learning (ICML-11) June 2011 Bellevue WA USA 809\u2013816."},{"key":"e_1_2_9_7_2","unstructured":"BerantJ. ChouA. RoyF. andLiangP. Semantic parsing on freebase from question-answer pairs Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing October 2013 Seattle WA USA Association for Computational Linguistics 1533\u20131544."},{"key":"e_1_2_9_8_2","doi-asserted-by":"crossref","unstructured":"BollackerK. D. EvansC. ParitoshP. SturgeT. andTaylorJ. Freebase: a collaboratively created graph database for structuring human knowledge Proceedings of the 2008 ACM SIGMOD International Conference on Management of Data June 2008 Vancouver Canada ACM 1247\u20131250 https:\/\/doi.org\/10.1145\/1376616.1376746 2-s2.0-57149137628.","DOI":"10.1145\/1376616.1376746"},{"key":"e_1_2_9_9_2","doi-asserted-by":"publisher","DOI":"10.1023\/B:BTTJ.0000047600.45421.6d"},{"key":"e_1_2_9_10_2","doi-asserted-by":"crossref","unstructured":"ManningC. SurdeanuM. BauerJ. FinkelJ. BethardS. andMcCloskyD. The stanford CoreNLP natural language processing toolkit Proceedings of 52nd Annual Meeting of the Association for Computational Linguistics: System Demonstrations June 2014 Baltimore MD USA Association for Computational Linguistics 55\u201360 https:\/\/doi.org\/10.3115\/v1\/P14-5010.","DOI":"10.3115\/v1\/P14-5010"},{"key":"e_1_2_9_11_2","doi-asserted-by":"crossref","unstructured":"PenningtonJ. SocherR. andManningC. GloVe: global vectors for word representation Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) October 2014 Doha Qatar Association for Computational Linguistics 1532\u20131543 https:\/\/doi.org\/10.3115\/v1\/D14-1162.","DOI":"10.3115\/v1\/D14-1162"},{"key":"e_1_2_9_12_2","unstructured":"NiL. MitchellT. andWilliam CohenW. Random walk inference and learning in a large scale knowledge base Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing July 2011 Edinburgh UK Association for Computational Linguistics 529\u2013539."},{"key":"e_1_2_9_13_2","unstructured":"BrochelerM. MihalkovaL. andGetoorL. Probabilistic similarity logic Proceedings of the Conference on Uncertainty in Artificial Intelligence (UAI) August 2012 Catalina Island CA USA."},{"key":"e_1_2_9_14_2","doi-asserted-by":"crossref","unstructured":"WeiZ. ZhaoJ. andLiuK. Mining inference formulas by goal-directed random walks Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing November 2016 Austin TX USA Association for Computational Linguistics 1379\u20131388 https:\/\/doi.org\/10.18653\/v1\/D16-1145.","DOI":"10.18653\/v1\/D16-1145"},{"key":"e_1_2_9_15_2","doi-asserted-by":"crossref","unstructured":"WeiZ. ZhaoJ. LiuK. QiZ. SunZ. andTianG. Large-scale knowledge base completion: inferring via grounding network sampling over selected instances Proceedings of the 24th ACM International on Conference on Information and Knowledge Management October 2015 Melbourne Australia ACM 1331\u20131340 https:\/\/doi.org\/10.1145\/2806416.2806513 2-s2.0-84958248229.","DOI":"10.1145\/2806416.2806513"},{"key":"e_1_2_9_16_2","unstructured":"AntoineB. UsunierN. ChopraS. andWestonJ. Large-scale simple question answering with memory networks 2015 http:\/\/arxiv.org\/abs\/1506.02075."},{"key":"e_1_2_9_17_2","unstructured":"RichardsonM. BurgesC. J. C. andRenshawE. MCTEST: a challenge dataset for the open-domain machine comprehension of text Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing October 2013 Seattle WA USA."},{"key":"e_1_2_9_18_2","unstructured":"HillF. BordesA. ChopraS. andWestonJ. The goldilocks principle: reading children\u2019s books with explicit memory representations Proceedings of the International Conference on Learning Representations (ICLR) May 2015 San Diego CA USA."},{"key":"e_1_2_9_19_2","unstructured":"HermannK. M. KociskyT. GrefenstetteE.et al. Teaching machines to read and comprehend Proceedings of the Advances in Neural Information Processing Systems (NIPS) December 2015 Montreal Canada 1693\u20131701."},{"key":"e_1_2_9_20_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 November 2016 Austin TX USA Association for Computational Linguistics 2383\u20132392 https:\/\/doi.org\/10.18653\/v1\/D16-1264.","DOI":"10.18653\/v1\/D16-1264"},{"key":"e_1_2_9_21_2","doi-asserted-by":"crossref","unstructured":"ClarkP. EtzioniO. KhotT.et al. Combining retrieval statistics and inference to answer elementary science questions Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence February 2016 Phoenix AZ USA 2580\u20132586.","DOI":"10.1609\/aaai.v30i1.10325"},{"key":"e_1_2_9_22_2","doi-asserted-by":"crossref","unstructured":"KhotT. BalasubramanianN. GribkoffE. SabharwalA. ClarkP. andEtzioniO. Exploring markov logic networks for question answering Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing September 2015 Lisbon Portugal Association for Computational Linguistics 685\u2013694 https:\/\/doi.org\/10.18653\/v1\/D15-1080.","DOI":"10.18653\/v1\/D15-1080"},{"key":"e_1_2_9_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2020.2963848"},{"key":"e_1_2_9_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/lgrs.2019.2936652"},{"key":"e_1_2_9_25_2","unstructured":"WangW. Y.andCohenW. W. Learning first-order logic embeddings via matrix factorization Proceedings of the 25th International Joint Conference on Artificial Intelligence (IJCAI 2016) July 2016 New York NY USA."},{"key":"e_1_2_9_26_2","doi-asserted-by":"crossref","unstructured":"LinY. LiuZ. SunM. LiuY. andZhuX. Learning entity and relation embeddings for knowledge graph completion Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence January 2015 Austin TX USA 2181\u20132187.","DOI":"10.1609\/aaai.v29i1.9491"},{"key":"e_1_2_9_27_2","doi-asserted-by":"crossref","unstructured":"LinY. LiuZ. LuanH. SunM. RaoS. andLiuS. Modeling relation paths for representation learning of knowledge bases Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing September 2015 Lisbon Portugal Association for Computational Linguistics 705\u2013714 https:\/\/doi.org\/10.18653\/v1\/D15-1082.","DOI":"10.18653\/v1\/D15-1082"},{"key":"e_1_2_9_28_2","doi-asserted-by":"crossref","unstructured":"NeelakantanA. RothB. andMcCallumA. Compositional vector space models for knowledge base completion 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) July 2015 Beijing China Association for Computational Linguistics 156\u2013166 https:\/\/doi.org\/10.3115\/v1\/P15-1016.","DOI":"10.3115\/v1\/P15-1016"},{"key":"e_1_2_9_29_2","unstructured":"SocherR. ChenD. ManningC. D. andNgA. Reasoning with neural tensor networks for knowledge base completion Proceedings of the Advances in Neural Information Processing Systems (NIPS) December 2019 Sydney Australia 926\u2013934."},{"key":"e_1_2_9_30_2","doi-asserted-by":"crossref","unstructured":"GuuK. MillerJ. andLiangP. Traversing knowledge graphs in vector space Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing September 2015 Lisbon Portugal Association for Computational Linguistics 318\u2013327.","DOI":"10.18653\/v1\/D15-1038"},{"key":"e_1_2_9_31_2","doi-asserted-by":"crossref","unstructured":"WangZ. ZhangJ. FengJ. andChenZ. Knowledge graph embedding by translating on hyperplanes Proceedings of the Twenty-Eighth AAAI Conference on Artificial Intelligence July 2014 Qu\u00e9bec City Canada Citeseer 1112\u20131119.","DOI":"10.1609\/aaai.v28i1.8870"}],"container-title":["Computational Intelligence and Neuroscience"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/downloads.hindawi.com\/journals\/cin\/2021\/6689740.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/cin\/2021\/6689740.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/2021\/6689740","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,6]],"date-time":"2024-08-06T11:18:58Z","timestamp":1722943138000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1155\/2021\/6689740"}},"subtitle":[],"editor":[{"given":"Qiangqiang","family":"Yuan","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\/6689740"],"URL":"https:\/\/doi.org\/10.1155\/2021\/6689740","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":"2020-10-24","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-01-30","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-02-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"6689740"}}