{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,15]],"date-time":"2025-07-15T03:29:35Z","timestamp":1752550175983},"publisher-location":"California","reference-count":0,"publisher":"International Joint Conferences on Artificial Intelligence Organization","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,7]]},"abstract":"<jats:p>The lack of sufficient training data in many domains, poses a major challenge to the construction of domain-specific machine reading comprehension (MRC) models with satisfying performance. In this paper, we propose a novel iterative multi-source mutual knowledge transfer framework for MRC. As an extension of the conventional knowledge transfer with one-to-one correspondence, our framework focuses on the many-to-many mutual transfer, which involves synchronous executions of multiple many-to-one transfers in an iterative manner.Specifically, to update a target-domain MRC model, we first consider other domain-specific MRC models as individual teachers, and employ knowledge distillation to train a multi-domain MRC model, which is differentially required to fit the training data and match the outputs of these individual models according to their domain-level similarities to the target domain. After being initialized by the multi-domain MRC model, the target-domain MRC model is fine-tuned to match both its training data and the output of its previous best model simultaneously via knowledge distillation. Compared with previous approaches, our framework can continuously enhance all domain-specific MRC models by enabling each model to iteratively and differentially absorb the domain-shared knowledge from others. Experimental results and in-depth analyses on several benchmark datasets demonstrate the effectiveness of our framework.<\/jats:p>","DOI":"10.24963\/ijcai.2020\/525","type":"proceedings-article","created":{"date-parts":[[2020,7,8]],"date-time":"2020-07-08T08:12:10Z","timestamp":1594195930000},"page":"3794-3800","source":"Crossref","is-referenced-by-count":5,"title":["An Iterative Multi-Source Mutual Knowledge Transfer Framework for Machine Reading Comprehension"],"prefix":"10.24963","author":[{"given":"Xin","family":"Liu","sequence":"first","affiliation":[{"name":"Xiamen University, Xiamen, China"}]},{"given":"Kai","family":"Liu","sequence":"additional","affiliation":[{"name":"Baidu Inc., Beijing, China"}]},{"given":"Xiang","family":"Li","sequence":"additional","affiliation":[{"name":"Xiaomi AI Lab, Xiaomi Inc., Beijing, China"}]},{"given":"Jinsong","family":"Su","sequence":"additional","affiliation":[{"name":"Xiamen University, Xiamen, China"}]},{"given":"Yubin","family":"Ge","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign, Urbana, IL 61801, USA"}]},{"given":"Bin","family":"Wang","sequence":"additional","affiliation":[{"name":"Xiaomi AI Lab, Xiaomi Inc., Beijing, China"}]},{"given":"Jiebo","family":"Luo","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Rochester, Rochester NY 14627, USA"}]}],"member":"10584","event":{"number":"28","sponsor":["International Joint Conferences on Artificial Intelligence Organization (IJCAI)"],"acronym":"IJCAI-PRICAI-2020","name":"Twenty-Ninth International Joint Conference on Artificial Intelligence and Seventeenth Pacific Rim International Conference on Artificial Intelligence {IJCAI-PRICAI-20}","start":{"date-parts":[[2020,7,11]]},"theme":"Artificial Intelligence","location":"Yokohama, Japan","end":{"date-parts":[[2020,7,17]]}},"container-title":["Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence"],"original-title":[],"deposited":{"date-parts":[[2020,7,8]],"date-time":"2020-07-08T22:15:43Z","timestamp":1594246543000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2020\/525"}},"subtitle":[],"proceedings-subject":"Artificial Intelligence Research Articles","short-title":[],"issued":{"date-parts":[[2020,7]]},"references-count":0,"URL":"https:\/\/doi.org\/10.24963\/ijcai.2020\/525","relation":{},"subject":[],"published":{"date-parts":[[2020,7]]}}}