{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T14:15:37Z","timestamp":1753884937740,"version":"3.41.2"},"reference-count":27,"publisher":"World Scientific Pub Co Pte Ltd","issue":"06","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int. J. Human. Robot."],"published-print":{"date-parts":[[2021,12]]},"abstract":"<jats:p> Linguistic intelligence and the ability to converse with human are important and indispensable parts of humanoid robots. One of the most challenging tasks in knowledge-grounded task-oriented dialog systems (KTDS) is the knowledge selection task, which aims to find the proper knowledge snippets to respond to user dialog requests. In this paper, we first propose domain adapted-BERT (DA-BERT) which employs pre-trained bidirectional encoder representations from transformers (BERT) with domain adaptive training and dynamic masking probability for knowledge selection in KTDS. Domain adaptive training can minimize the domain gap between the general text data that BERT is pre-trained on and the dialog\u2013knowledge joint data while dynamic masking probability enhances the training in an easy-to-hard manner. After knowledge selection, the next task in KTDS is knowledge-grounded generation. To improve the performance in knowledge-grounded generation, we propose GPT-PR to employ post-ranking on the generator\u2019s outputs. Post-ranking eliminates the possibility of generating hallucination response by a large portion during the sampling-based decoding process and thus can improve the quality of the generated response. Experimental results on the benchmark dataset show that our proposed pre-training and post-ranking methods, DA-BERT and GPT-PR, respectively, outperform the state-of-the-art models with large margins across all the evaluation metrics. Moreover, in the experiments, we also analyze the bad cases of DA-BERT and GPT-PR and do visualizations to facilitate further research in this direction. <\/jats:p>","DOI":"10.1142\/s0219843621500195","type":"journal-article","created":{"date-parts":[[2022,1,19]],"date-time":"2022-01-19T07:52:53Z","timestamp":1642578773000},"source":"Crossref","is-referenced-by-count":1,"title":["Improving Dialog System Grounded with Unstructured Knowledge by Domain Adaptive Pre-Training and Post-Ranking"],"prefix":"10.1142","volume":"18","author":[{"given":"Zhi","family":"Zeng","sequence":"first","affiliation":[{"name":"Department of Computer Science, City University of Hong Kong, Hong Kong, P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kam-Yiu","family":"Lam","sequence":"additional","affiliation":[{"name":"Department of Computer Science, City University of Hong Kong, Hong Kong, P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chi-Yin","family":"Chow","sequence":"additional","affiliation":[{"name":"Department of Computer Science, City University of Hong Kong, Hong Kong, P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ning","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Computer Science, City University of Hong Kong, Hong Kong, P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"219","published-online":{"date-parts":[[2022,2,16]]},"reference":[{"volume-title":"Proc. Annual Meeting of the Special Interest Group on Discourse and Dialogue","year":"2020","author":"Kim S.","key":"S0219843621500195BIB001"},{"volume-title":"Proc. First Instructional Conf. Machine Learning","year":"2003","author":"Ramos J.","key":"S0219843621500195BIB002"},{"key":"S0219843621500195BIB003","doi-asserted-by":"publisher","DOI":"10.1561\/1500000019"},{"issue":"8","key":"S0219843621500195BIB004","first-page":"9","volume":"1","author":"Radford A.","year":"2019","journal-title":"OpenAI Blog"},{"volume-title":"Proc. Annual Conf. North American Chapter of the Association for Computational Linguistics","year":"2019","author":"Devlin J.","key":"S0219843621500195BIB005"},{"key":"S0219843621500195BIB010","first-page":"11328","volume-title":"Proc. 37th Int. Conf. Machine Learning","author":"Zhang J.","year":"2020"},{"key":"S0219843621500195BIB014","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.9"},{"key":"S0219843621500195BIB015","first-page":"311","volume-title":"Proc. 40th Annual Meeting of the Association for Computational Linguistics","author":"Papineni K.","year":"2002"},{"key":"S0219843621500195BIB016","first-page":"65","volume-title":"Proc. ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization","author":"Banerjee S.","year":"2005"},{"key":"S0219843621500195BIB017","first-page":"74","volume-title":"Text Summarization Branches Out","author":"Lin C.-Y.","year":"2004"},{"key":"S0219843621500195BIB018","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"S0219843621500195BIB019","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"volume-title":"Advances in Neural Information Processing Systems","year":"2017","author":"Vaswani A.","key":"S0219843621500195BIB020"},{"key":"S0219843621500195BIB025","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1299"},{"key":"S0219843621500195BIB026","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1130"},{"key":"S0219843621500195BIB031","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1547"},{"key":"S0219843621500195BIB032","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W16-6626"},{"key":"S0219843621500195BIB033","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1202"},{"volume-title":"Proc. Int. Conf. Learning Representations","year":"2019","author":"Clark K.","key":"S0219843621500195BIB034"},{"key":"S0219843621500195BIB035","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-demos.30"},{"key":"S0219843621500195BIB036","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3412330"},{"key":"S0219843621500195BIB037","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2153"},{"key":"S0219843621500195BIB038","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401255"},{"issue":"140","key":"S0219843621500195BIB040","first-page":"1","volume":"21","author":"Raffel C.","year":"2020","journal-title":"J. Mach. Learn. Res."},{"journal-title":"OpenReview","year":"2019","author":"Eric M.","key":"S0219843621500195BIB041"},{"key":"S0219843621500195BIB042","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00300"},{"key":"S0219843621500195BIB043","first-page":"3319","volume-title":"Int. Conf. Machine Learning","author":"Sundararajan M.","year":"2017"}],"container-title":["International Journal of Humanoid Robotics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.worldscientific.com\/doi\/pdf\/10.1142\/S0219843621500195","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,3,18]],"date-time":"2022-03-18T05:29:23Z","timestamp":1647581363000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.worldscientific.com\/doi\/abs\/10.1142\/S0219843621500195"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12]]},"references-count":27,"journal-issue":{"issue":"06","published-print":{"date-parts":[[2021,12]]}},"alternative-id":["10.1142\/S0219843621500195"],"URL":"https:\/\/doi.org\/10.1142\/s0219843621500195","relation":{},"ISSN":["0219-8436","1793-6942"],"issn-type":[{"type":"print","value":"0219-8436"},{"type":"electronic","value":"1793-6942"}],"subject":[],"published":{"date-parts":[[2021,12]]},"article-number":"2150019"}}