{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T09:12:16Z","timestamp":1778663536218,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":45,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,10,26]],"date-time":"2021-10-26T00:00:00Z","timestamp":1635206400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100004663","name":"Ministry of Science and Technology, Taiwan","doi-asserted-by":"publisher","award":["MOST 110-2221-E-A49-073-MY3"],"award-info":[{"award-number":["MOST 110-2221-E-A49-073-MY3"]}],"id":[{"id":"10.13039\/501100004663","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,10,26]]},"DOI":"10.1145\/3459637.3482333","type":"proceedings-article","created":{"date-parts":[[2021,11,15]],"date-time":"2021-11-15T15:31:16Z","timestamp":1636990276000},"page":"1548-1557","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["Corrective Guidance and Learning for Dialogue Management"],"prefix":"10.1145","author":[{"given":"Mahdin","family":"Rohmatillah","sequence":"first","affiliation":[{"name":"National Yang Ming Chiao Tung University, Hsinchu, Taiwan Roc"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jen-Tzung","family":"Chien","sequence":"additional","affiliation":[{"name":"National Yang Ming Chiao Tung University, Hsinchu, Taiwan Roc"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2021,10,30]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Agent-Agnostic Human-in-the-Loop Reinforcement Learning. In NIPS Workshop on the Future of Interactive Learning Machines.","author":"Abel David","year":"2016"},{"key":"e_1_3_2_1_2_1","volume-title":"Learning end-to-end goal-oriented dialog. arXiv preprint arXiv:1605.07683","author":"Bordes Antoine","year":"2016"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1547"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1459"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2428632"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-4006"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11265-013-0759-x"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1313"},{"key":"e_1_3_2_1_9_1","volume-title":"Proc. of Asia-Pacific Signal and Information Processing Association Annual Summit and Conference. 1611--1616","author":"Chien Jen-Tzung","year":"2020"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2499302"},{"key":"e_1_3_2_1_11_1","volume-title":"Proc. of European Signal Processing Conference. 1527--1531","author":"Chien Jen-Tzung","year":"2020"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1383"},{"key":"e_1_3_2_1_13_1","volume-title":"Diluted Near-Optimal Expert Demonstrations for Guiding Dialogue Stochastic Policy Optimisation. In NIPS Workshop on Human in the Loop Dialogue Systems.","author":"Cordier Thibault","year":"2020"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-35142-6_14"},{"key":"e_1_3_2_1_15_1","volume-title":"Proc. of North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 4171--4186","author":"Devlin Jacob","year":"2019"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357940"},{"key":"e_1_3_2_1_17_1","volume-title":"Multi-Domain Dialogue State Corrections and State Tracking Baselines. arXiv preprint arXiv:1907.01669","author":"Eric Mihail","year":"2019"},{"key":"e_1_3_2_1_18_1","volume-title":"Learning robust rewards with adversarial inverse reinforcement learning. arXiv preprint arXiv:1710.11248","author":"Fu Justin","year":"2017"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3269206.3271683"},{"key":"e_1_3_2_1_20_1","volume-title":"Proc. of the International Conference on Learning Representations.","author":"Diederik"},{"key":"e_1_3_2_1_21_1","volume-title":"Tom\u00e1vs Nekvinda, and Ondvr ej Duvs ek.","author":"Kulh\u00e1nek Jon\u00e1vs","year":"2021"},{"key":"e_1_3_2_1_22_1","volume-title":"AAAI Workshop on Dialog System Technology Challenge.","author":"Li Jinchao","year":"2021"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.209"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1203"},{"key":"e_1_3_2_1_25_1","volume-title":"Language Models are Unsupervised Multitask Learners. OpenAI blog","author":"Radford Alec","year":"2019"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6394"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-534"},{"key":"e_1_3_2_1_28_1","volume-title":"Proc. of International Conference on Artificial Intelligence and Statistics","volume":"15","author":"Ross Stephane","year":"2011"},{"key":"e_1_3_2_1_29_1","volume-title":"Proc. of International Conference on Learning Representations.","author":"Schulman John","year":"2016"},{"key":"e_1_3_2_1_30_1","volume-title":"Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347","author":"Schulman John","year":"2017"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.5555\/1605285.1605288"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1416"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.59"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1010"},{"key":"e_1_3_2_1_35_1","volume-title":"Proc. of Annual Meeting of the Special Interest Group on Discourse and Dialogue. 297--310","author":"Takanobu Ryuichi","year":"2020"},{"key":"e_1_3_2_1_36_1","first-page":"26","article-title":"Divide the gradient by a running average of its recent magnitude","volume":"4","author":"Tieleman Tijmen","year":"2012","journal-title":"COURSERA: Neural Networks for Machine Learning"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.12625"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-4013"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.5555\/2846250"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1233"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33017289"},{"key":"e_1_3_2_1_42_1","volume-title":"A Hybrid Task-Oriented Dialog System with Domain and Task Adaptive Pretraining. arXiv preprint arXiv:2102.04506","author":"Zhang Boliang","year":"2021"},{"key":"e_1_3_2_1_43_1","volume-title":"Recent advances and challenges in task-oriented dialog systems. Science China Technological Sciences","author":"Zhang Zheng","year":"2020"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6516"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-demos.19"}],"event":{"name":"CIKM '21: The 30th ACM International Conference on Information and Knowledge Management","location":"Virtual Event Queensland Australia","acronym":"CIKM '21","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 30th ACM International Conference on Information & Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3459637.3482333","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3459637.3482333","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:12:22Z","timestamp":1750191142000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3459637.3482333"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,26]]},"references-count":45,"alternative-id":["10.1145\/3459637.3482333","10.1145\/3459637"],"URL":"https:\/\/doi.org\/10.1145\/3459637.3482333","relation":{},"subject":[],"published":{"date-parts":[[2021,10,26]]},"assertion":[{"value":"2021-10-30","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}