{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,5]],"date-time":"2025-03-05T05:48:10Z","timestamp":1741153690659,"version":"3.38.0"},"reference-count":32,"publisher":"China Science Publishing & Media Ltd.","issue":"3","license":[{"start":{"date-parts":[[2023,9,12]],"date-time":"2023-09-12T00:00:00Z","timestamp":1694476800000},"content-version":"vor","delay-in-days":254,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["direct.mit.edu"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,8,1]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n               <jats:p>Machine reading comprehension has been a research focus in natural language processing and intelligence engineering. However, there is a lack of models and datasets for the MRC tasks in the anti-terrorism domain. Moreover, current research lacks the ability to embed accurate background knowledge and provide precise answers. To address these two problems, this paper first builds a text corpus and testbed that focuses on the anti-terrorism domain in a semi-automatic manner. Then, it proposes a knowledge-based machine reading comprehension model that fuses domain-related triples from a large-scale encyclopedic knowledge base to enhance the semantics of the text. To eliminate knowledge noise that could lead to semantic deviation, this paper uses a mixed mutual attention mechanism among questions, passages, and knowledge triples to select the most relevant triples before embedding their semantics into the sentences. Experiment results indicate that the proposed approach can achieve a 70.70% EM value and an 87.91% F1 score, with a 4.23% and 3.35% improvement over existing methods, respectively.<\/jats:p>","DOI":"10.1162\/dint_a_00210","type":"journal-article","created":{"date-parts":[[2023,9,12]],"date-time":"2023-09-12T15:38:00Z","timestamp":1694533080000},"page":"685-706","update-policy":"https:\/\/doi.org\/10.1162\/mitpressjournals.corrections.policy","source":"Crossref","is-referenced-by-count":2,"title":["Knowledge Graph based Mutual Attention for Machine Reading Comprehension over Anti-Terrorism Corpus"],"prefix":"10.3724","volume":"5","author":[{"given":"Feng","family":"Gao","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Wuhan University of Science and Technology, Wuhan 430065, Hubei"},{"name":"The Key Laboratory of Rich-Media Knowledge Organization and Service of Digital Publishing Content, Institute of Scientific and Technical Information of China, Beijing 100038, China"},{"name":"Wuhan University of Science and Technology Big Data Science and Engineering Research Institute, Wuhan 430065, Hubei"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jin","family":"Hou","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Wuhan University of Science and Technology, Wuhan 430065, Hubei"},{"name":"The Key Laboratory of Rich-Media Knowledge Organization and Service of Digital Publishing Content, Institute of Scientific and Technical Information of China, Beijing 100038, China"},{"name":"Wuhan University of Science and Technology Big Data Science and Engineering Research Institute, Wuhan 430065, Hubei"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinguang","family":"Gu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Wuhan University of Science and Technology, Wuhan 430065, Hubei"},{"name":"The Key Laboratory of Rich-Media Knowledge Organization and Service of Digital Publishing Content, Institute of Scientific and Technical Information of China, Beijing 100038, China"},{"name":"Wuhan University of Science and Technology Big Data Science and Engineering Research Institute, Wuhan 430065, Hubei"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lihua","family":"Zhang","sequence":"additional","affiliation":[{"name":"Eastchina Jiaotong University, Nanchang 330013, Jiangxi"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"2026","published-online":{"date-parts":[[2023,8,1]]},"reference":[{"key":"2023091215374668800_ref1","doi-asserted-by":"crossref","first-page":"1006","DOI":"10.1109\/ICCMC53470.2022.9754070","article-title":"Survey of Machine Reading Comprehension Models and its Evaluation Metrics","volume-title":"2022 6th International Conference on Computing Methodologies and Communication (ICCMC)","author":"Therasa","year":"2022,"},{"issue":"20","key":"2023091215374668800_ref2","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"3","key":"2023091215374668800_ref3","doi-asserted-by":"crossref","first-page":"471","DOI":"10.1162\/dint_a_00154","article-title":"COKG-QA: Multi-hop Question Answering over COVID-19 Knowledge Graphs","volume":"4","author":"Du","year":"2022","journal-title":"Data Intelligence"},{"issue":"5","key":"2023091215374668800_ref4","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3527631","article-title":"New vietnamese corpus for machine reading comprehension of health news articles","volume":"21","author":"Van Nguyen","year":"2022","journal-title":"Transactions on Asian and Low-Resource Language Information Processing"},{"key":"2023091215374668800_ref5","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2022.emnlp-main.465","article-title":"IDK-MRC: Unanswerable Questions for Indonesian Machine Reading Comprehension","volume-title":"arXiv preprint arXiv:2210.13778","author":"Putri","year":"2022"},{"key":"2023091215374668800_ref6","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume-title":"arXiv:1810.04805","author":"Devlin","year":"2018"},{"key":"2023091215374668800_ref7","article-title":"Roberta: A robustly optimized bert pretraining approach","volume-title":"arXiv:1907.11692","author":"Liu","year":"2019"},{"key":"2023091215374668800_ref8","first-page":"64","article-title":"Spanbert: Improving pre-training by representing and predicting spans","volume-title":"Transactions of the Association for Computational Linguistics","author":"Joshi","year":"2020"},{"key":"2023091215374668800_ref9","article-title":"Albert: A lite bert for self-supervised learning of language representations","volume-title":"arXiv:1909.11942","author":"Lan","year":"2019"},{"key":"2023091215374668800_ref10","doi-asserted-by":"crossref","first-page":"2346","DOI":"10.18653\/v1\/P19-1226","article-title":"Enhancing pre-trained language representations with rich knowledge for machine reading comprehension","volume-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","author":"Yang","year":"2019"},{"key":"2023091215374668800_ref11","article-title":"A Survey on Multi-hop Question Answering and Generation","volume-title":"arXiv preprint arXiv:2204.09140","author":"Mavi","year":"2022"},{"key":"2023091215374668800_ref12","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/P19-1139","article-title":"ERNIE: Enhanced language representation with informative entities","volume-title":"arXiv:1905.07129","author":"Zhang","year":"2019"},{"key":"2023091215374668800_ref13","doi-asserted-by":"crossref","first-page":"1427","DOI":"10.18653\/v1\/2020.emnlp-main.111","article-title":"Towards medical machine reading comprehension with structural knowledge and plain text","volume-title":"Proceedings of the 2020 conference on empirical methods in natural language processing (EMNLP)","author":"Li","year":"2020,"},{"issue":"2","key":"2023091215374668800_ref14","doi-asserted-by":"crossref","first-page":"125","DOI":"10.37936\/ecticit.2022162.247799","article-title":"Machine Reading Comprehension Using Multi-Passage BERT with Dice Loss on Thai Corpus","volume":"16","author":"Lapchaicharoenkit","year":"2022","journal-title":"ECTI Transactions on Computer and Information Technology (ECTI-CIT)"},{"key":"2023091215374668800_ref15","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/D16-1264","article-title":"Squad: 100,000+ questions for machine comprehension of text","volume-title":"arXiv:1606.05250","author":"Rajpurkar","year":"2016"},{"key":"2023091215374668800_ref16","article-title":"DuReader: a Chinese Machine Reading Comprehension Dataset from Real-world Applications","volume-title":"arXiv:1711.05073","author":"Wei","year":"2017"},{"key":"2023091215374668800_ref17","article-title":"Teaching Machines to Read and Comprehend","volume-title":"Advances in Neural Information Processing Systems","author":"Karl Moritz","year":"2015"},{"key":"2023091215374668800_ref18","article-title":"A span-extraction dataset for Chinese machine reading comprehension","volume-title":"arXiv:1810.07366","author":"Cui","year":"2018"},{"issue":"5","key":"2023091215374668800_ref19","doi-asserted-by":"crossref","first-page":"8968","DOI":"10.1609\/aaai.v34i05.6428","article-title":"Ernie 2.0: A continual pre-training framework for language understanding","volume":"34","author":"Sun","year":"2020","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"2023091215374668800_ref20","article-title":"A survey of knowledge enhanced pre-trained models","volume-title":"arXiv preprint arXiv:2110.00269","author":"Yang","year":"2021"},{"key":"2023091215374668800_ref21","first-page":"3011","article-title":"Syntaxbert: Improving pre-trained transformers with syntax trees","volume-title":"Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume","author":"Bai","year":"2021"},{"key":"2023091215374668800_ref22","article-title":"Integrating graph contextualized knowledge into pretrained language models","volume-title":"arXiv preprint arXiv:1912.00147","author":"He","year":"2019"},{"key":"2023091215374668800_ref23","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1016\/j.aiopen.2021.06.004","article-title":"Cokebert: Contextual knowledge selection and embedding towards enhanced pre-trained language models","volume":"2","author":"Su","year":"2021","journal-title":"AI Open"},{"key":"2023091215374668800_ref24","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2022.naacl-main.372","article-title":"JointLK: Joint Reasoning with Language Models and Knowledge Graphs for Commonsense Question Answering","volume-title":"NAACL-HLT","author":"Sun","year":"2022"},{"issue":"3","key":"2023091215374668800_ref25","doi-asserted-by":"crossref","first-page":"2901","DOI":"10.1609\/aaai.v34i03.5681","article-title":"K-bert: Enabling language representation with knowledge graph","volume":"34","author":"Liu","year":"2020","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"2023091215374668800_ref26","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2020.coling-main.327","article-title":"Colake: Contextualized language and knowledge embedding","volume-title":"arXiv:2010.00309","author":"Sun","year":"2020"},{"key":"2023091215374668800_ref27","doi-asserted-by":"crossref","first-page":"176","DOI":"10.1162\/tacl_a_00360","article-title":"Kepler: A unified model for knowledge embedding and pretrained language representation","volume":"9","author":"Wang","year":"2021","journal-title":"Transactions of the Association for Computational Linguistics"},{"issue":"7","key":"2023091215374668800_ref28","doi-asserted-by":"crossref","first-page":"6418","DOI":"10.1609\/aaai.v35i7.16796","article-title":"Kg-bart: Knowledge graph-augmented bart for generative commonsense reasoning","volume":"35","author":"Liu","year":"2021","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"2023091215374668800_ref29","article-title":"Bidirectional attention flow for machine comprehension","volume-title":"arXiv:1611.01603","author":"Seo","year":"2016"},{"key":"2023091215374668800_ref30","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/D19-3041","article-title":"UER: An open-source toolkit for pre-training models","volume-title":"arXiv preprint arXiv:1909.05658","author":"Zhao","year":"2019"},{"key":"2023091215374668800_ref31","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2020.findings-emnlp.58","article-title":"Revisiting pre-trained models for Chinese natural language processing","volume-title":"arXiv:2004.13922","author":"Cui","year":"2020"},{"key":"2023091215374668800_ref32","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/D19-1169","article-title":"Cross-lingual machine reading comprehension","volume-title":"arXiv:1909.00361","author":"Cui","year":"2019"}],"container-title":["Data Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/direct.mit.edu\/dint\/article-pdf\/5\/3\/685\/2158230\/dint_a_00210.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/direct.mit.edu\/dint\/article-pdf\/5\/3\/685\/2158230\/dint_a_00210.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,4]],"date-time":"2025-03-04T23:06:24Z","timestamp":1741129584000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/dint\/article\/5\/3\/685\/117370\/Knowledge-Graph-based-Mutual-Attention-for-Machine"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":32,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2023,8,1]]}},"URL":"https:\/\/doi.org\/10.1162\/dint_a_00210","relation":{},"ISSN":["2641-435X"],"issn-type":[{"type":"electronic","value":"2641-435X"}],"subject":[],"published-other":{"date-parts":[[2023]]},"published":{"date-parts":[[2023]]}}}