{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T01:36:07Z","timestamp":1777599367401,"version":"3.51.4"},"reference-count":43,"publisher":"China Science Publishing & Media Ltd.","issue":"3","license":[{"start":{"date-parts":[[2022,8,10]],"date-time":"2022-08-10T00:00:00Z","timestamp":1660089600000},"content-version":"vor","delay-in-days":221,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["direct.mit.edu"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,7,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>COVID-19 evolves rapidly and an enormous number of people worldwide desire instant access to COVID-19 information such as the overview, clinic knowledge, vaccine, prevention measures, and COVID-19 mutation. Question answering (QA) has become the mainstream interaction way for users to consume the ever-growing information by posing natural language questions. Therefore, it is urgent and necessary to develop a QA system to offer consulting services all the time to relieve the stress of health services. In particular, people increasingly pay more attention to complex multi-hop questions rather than simple ones during the lasting pandemic, but the existing COVID-19 QA systems fail to meet their complex information needs. In this paper, we introduce a novel multi-hop QA system called COKG-QA, which reasons over multiple relations over large-scale COVID-19 Knowledge Graphs to return answers given a question. In the field of question answering over knowledge graph, current methods usually represent entities and schemas based on some knowledge embedding models and represent questions using pre-trained models. While it is convenient to represent different knowledge (i.e., entities and questions) based on specified embeddings, an issue raises that these separate representations come from heterogeneous vector spaces. We align question embeddings with knowledge embeddings in a common semantic space by a simple but effective embedding projection mechanism. Furthermore, we propose combining entity embeddings with their corresponding schema embeddings which served as important prior knowledge, to help search for the correct answer entity of specified types. In addition, we derive a large multi-hop Chinese COVID-19 dataset (called COKG-DATA for remembering) for COKG-QA based on the linked knowledge graph OpenKG-COVID19 launched by OpenKG\u2460, including comprehensive and representative information about COVID-19. COKG-QA achieves quite competitive performance in the 1-hop and 2-hop data while obtaining the best result with significant improvements in the 3-hop. And it is more efficient to be used in the QA system for users. Moreover, the user study shows that the system not only provides accurate and interpretable answers but also is easy to use and comes with smart tips and suggestions.<\/jats:p>","DOI":"10.1162\/dint_a_00154","type":"journal-article","created":{"date-parts":[[2022,8,10]],"date-time":"2022-08-10T19:14:43Z","timestamp":1660158883000},"page":"471-492","update-policy":"https:\/\/doi.org\/10.1162\/mitpressjournals.corrections.policy","source":"Crossref","is-referenced-by-count":20,"title":["COKG-QA: Multi-hop Question Answering over COVID-19 Knowledge\n                    Graphs"],"prefix":"10.3724","volume":"4","author":[{"given":"Huifang","family":"Du","sequence":"first","affiliation":[{"name":"College of Design and Innovation, Tongji University, Shanghai 200092, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhongwen","family":"Le","sequence":"additional","affiliation":[{"name":"School of Computer Science, Fudan University, Shanghai 200433, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haofen","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Design and Innovation, Tongji University, Shanghai 200092, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunwen","family":"Chen","sequence":"additional","affiliation":[{"name":"DataGrand Inc., Shanghai 201203, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Yu","sequence":"additional","affiliation":[{"name":"DataGrand Inc., Shanghai 201203, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"2026","published-online":{"date-parts":[[2022,7,1]]},"reference":[{"key":"2022081019142517100_ref1","first-page":"898","volume-title":"WULAI-QA: Web understanding and learning with AI towards\n                        document-based question answering against COVID-19","author":"Zhang","year":"2021"},{"key":"2022081019142517100_ref2","volume-title":"CAiRE-COVID: A question answering and query-focused multi-document\n                        summarization system for covid-19 scholarly information management","author":"Su","year":"2020"},{"key":"2022081019142517100_ref3","volume-title":"COVID-QA: A question answering dataset for COVID-19","author":"Moller","year":"2020"},{"key":"2022081019142517100_ref4","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2020.nlpcovid19-2.1","volume-title":"Answering questions on COVID-19 in real-time","author":"Lee","year":"2020"},{"key":"2022081019142517100_ref5","first-page":"4659","volume-title":"Research on question answering system for COVID-19 based on\n                        knowledge graph","author":"Ding","year":"2021"},{"key":"2022081019142517100_ref6","first-page":"294","volume-title":"Covid-on-the-Web: Knowledge graph and services to advance COVID-19\n                        research","author":"Michel","year":"2020"},{"key":"2022081019142517100_ref7","first-page":"215","volume-title":"The COVID-19 question answering system based on knowledge\n                        graph","author":"Sun","year":"2021"},{"issue":"5","key":"2022081019142517100_ref8","first-page":"115","article-title":"Optimizing automatic question answering system based on\n                        disease knowledge graph","volume":"5","author":"He","year":"2021","journal-title":"Data Analysis and Knowledge\n                        Discovery"},{"key":"2022081019142517100_ref9","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/D18-1455","volume-title":"Open domain question answering using early fusion of knowledge bases\n                        and text","author":"Sun","year":"2018"},{"key":"2022081019142517100_ref10","first-page":"2380","volume-title":"PullNet: Open domain question answering with iterative retrieval on\n                        knowledge bases and text","author":"Sun","year":"2019"},{"key":"2022081019142517100_ref11","first-page":"4498","volume-title":"Improving multi-hop question answering over knowledge graphs using\n                        knowledge base embeddings","author":"Saxena","year":"2020"},{"issue":"9","key":"2022081019142517100_ref12","doi-asserted-by":"crossref","first-page":"1332","DOI":"10.1093\/bioinformatics\/btaa834","article-title":"COVID-19 Knowledge Graph: a computable, multi-modal,\n                        cause-and-effect knowledge model of COVID-19\n                    pathophysiology","volume":"37","author":"Domingo-Fernandez","year":"2021","journal-title":"Bioinformatics"},{"issue":"7","key":"2022081019142517100_ref13","doi-asserted-by":"crossref","first-page":"998","DOI":"10.3390\/genes12070998","article-title":"Toward a coronavirus knowledge graph","volume":"12","author":"Zhang","year":"2021","journal-title":"Genes"},{"key":"2022081019142517100_ref14","volume-title":"KG-COVID-19: A framework to produce customized knowledge graphs for\n                        COVID-19 response","author":"Reese"},{"issue":"04","key":"2022081019142517100_ref15","doi-asserted-by":"crossref","first-page":"37215","DOI":"10.2196\/37215","article-title":"Construction of A Linked Dataset of COVID-19 Knowledge\n                        Graphs: Development and Applications","volume":"26","author":"Wang","year":"2022","journal-title":"JMIR Medical\n                        Informatics"},{"key":"2022081019142517100_ref16","first-page":"4659","volume-title":"Research on question answering system for COVID-19 based on\n                        knowledge graph","author":"Ding","year":"2021"},{"issue":"1","key":"2022081019142517100_ref17","first-page":"012136","article-title":"A general framework for Chinese domain knowledge graph\n                        question answering based on TransE","volume":"1693","author":"Pei","year":"2020","journal-title":"InJournal of\n                        Physics: Conference Series"},{"key":"2022081019142517100_ref18","article-title":"Translating embeddings for modeling multi-relational\n                        data","volume":"26","author":"Bordes","year":"2013","journal-title":"Advances in neural information processing\n                        systems"},{"issue":"3","key":"2022081019142517100_ref19","first-page":"2021026","article-title":"Progress, challenges and research trends of reasoning in\n                        multi-hop knowledge graph based question answering","volume":"7","author":"Du","year":"2021","journal-title":"Big Data Research"},{"key":"2022081019142517100_ref20","first-page":"2030","volume-title":"Embedding logical queries on knowledge graphs","author":"Hamilton","year":"2018"},{"key":"2022081019142517100_ref21","volume-title":"Query2box: Reasoning over knowledge graphs in vector space using box\n                        embeddings","author":"Ren","year":"2018"},{"key":"2022081019142517100_ref22","first-page":"33","volume-title":"Beta embeddings for multi-hop logical reasoning in knowledge\n                        graphs","author":"Ren","year":"2020"},{"key":"2022081019142517100_ref23","first-page":"833","volume-title":"Improving learning and inference in a large knowledge-base using\n                        latent syntactic cues","author":"Gardner","year":"2013"},{"key":"2022081019142517100_ref24","first-page":"564","volume-title":"DeepPath: A reinforcement learning method for knowledge graph\n                        reasoning","author":"Xiong","year":"2017"},{"key":"2022081019142517100_ref25","first-page":"553","volume-title":"Improving multi-hop knowledge base question answering by learning\n                        intermediate supervision signals","author":"He","year":"2021"},{"key":"2022081019142517100_ref26","first-page":"3137","volume-title":"Anytime bottom-up rule learning for knowledge graph\n                        completion","author":"Meilicke","year":"2019"},{"issue":"051","key":"2022081019142517100_ref27","first-page":"309","article-title":"Multi-hop knowledge graph reasoning with reward\n                        shaping","volume":"16","author":"Lin","year":"2019","journal-title":"United States Patent Application"},{"key":"2022081019142517100_ref28","first-page":"4149","volume-title":"TransferNet: An Effective and Transparent Framework for Multi-hop\n                        Question Answering over Relation Graph","author":"Shi","year":"2021"},{"key":"2022081019142517100_ref29","first-page":"2071","article-title":"Complex embeddings for simple link\n                    prediction","volume":"48","author":"Trouillon","year":"2016","journal-title":"Proceedings of the 33rd International\n                        Conference on International Conference on Machine Learning"},{"key":"2022081019142517100_ref30","first-page":"260","volume-title":"Question answering over Freebase with multi-column convolutional\n                        neural networks","author":"Dong","year":"2015"},{"key":"2022081019142517100_ref31","first-page":"165","volume-title":"Open question answering with weakly supervised embedding\n                        models","author":"Bordes","year":"2014"},{"key":"2022081019142517100_ref32","volume-title":"RoBERTa: A robustly optimized BERT pretraining approach","author":"Liu","year":"2019"},{"key":"2022081019142517100_ref33","first-page":"807","volume-title":"In defense of fully connected layers in visual representation\n                        transfer","author":"Zhang","year":"2017"},{"issue":"12","key":"2022081019142517100_ref34","doi-asserted-by":"crossref","first-page":"1407","DOI":"10.3390\/electronics10121407","article-title":"TransET: Knowledge graph embedding with entity\n                        types","volume":"10","author":"Wang","year":"2021","journal-title":"Electronics"},{"key":"2022081019142517100_ref35","first-page":"22152218","volume-title":"Learning entity type embeddings for knowledge graph\n                        completion","author":"Moon","year":"2017"},{"key":"2022081019142517100_ref36","volume-title":"Analysing mathematical reasoning abilities of neural\n                    models","author":"Saxton","year":"2018"},{"key":"2022081019142517100_ref37","first-page":"250","volume-title":"Tackling long-tailed relations and uncommon entities in knowledge\n                        graph completion","author":"Wang","year":"2019"},{"key":"2022081019142517100_ref38","first-page":"64426454","volume-title":"LUKE: Deep contextualized entity representations with entity-aware\n                        self-attention","author":"Yamada","year":"2020"},{"key":"2022081019142517100_ref39","first-page":"2187","volume-title":"Exploring conversational search with humans, assistants, and\n                        wizards","author":"Vtyurina","year":"2017"},{"key":"2022081019142517100_ref40","volume-title":"Conversational agents and community question answering","author":"Podgorny","year":"2019"},{"key":"2022081019142517100_ref41","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.12057","volume-title":"Variational reasoning for question answering with knowledge\n                        graph","author":"Zhang","year":"2018"},{"key":"2022081019142517100_ref42","first-page":"201","volume-title":"The value of semantic parse labeling for knowledge base question\n                        answering","author":"Yih","year":"2016"},{"issue":"Long Papers","key":"2022081019142517100_ref43","first-page":"641","article-title":"The Web as a Knowledge-Base for Answering Complex\n                        Questions","volume":"1","author":"Talmor","year":"2018","journal-title":"InProceedings of the 2018 Conference of\n                        the North American Chapter of the Association for Computational Linguistics:\n                        Human Language Technologies, Volume"}],"container-title":["Data Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/direct.mit.edu\/dint\/article-pdf\/4\/3\/471\/2038429\/dint_a_00154.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/direct.mit.edu\/dint\/article-pdf\/4\/3\/471\/2038429\/dint_a_00154.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,14]],"date-time":"2025-03-14T07:43:51Z","timestamp":1741938231000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.sciengine.com\/doi\/10.1162\/dint_a_00154"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":43,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2022,7,1]]}},"URL":"https:\/\/doi.org\/10.1162\/dint_a_00154","relation":{},"ISSN":["2641-435X"],"issn-type":[{"value":"2641-435X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2022]]},"published":{"date-parts":[[2022]]}}}