{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T01:09:01Z","timestamp":1784423341930,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":38,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,7,6]],"date-time":"2022-07-06T00:00:00Z","timestamp":1657065600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,7,6]]},"DOI":"10.1145\/3477495.3531844","type":"proceedings-article","created":{"date-parts":[[2022,7,7]],"date-time":"2022-07-07T15:12:13Z","timestamp":1657206733000},"page":"256-266","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":32,"title":["Learning to Infer User Implicit Preference in Conversational Recommendation"],"prefix":"10.1145","author":[{"given":"Chenhao","family":"Hu","sequence":"first","affiliation":[{"name":"Sun Yat-Sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuhua","family":"Huang","sequence":"additional","affiliation":[{"name":"Sun Yat-Sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yansen","family":"Zhang","sequence":"additional","affiliation":[{"name":"Sun Yat-Sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yubao","family":"Liu","sequence":"additional","affiliation":[{"name":"Sun Yat-Sen University & Guangdong Key Laboratory of Big Data Analysis and Processing, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2022,7,7]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"A survey of robot learning from demonstration. Robotics and autonomous systems","author":"Argall Brenna D","year":"2009","unstructured":"Brenna D Argall , Sonia Chernova , Manuela Veloso , and Brett Browning . 2009. A survey of robot learning from demonstration. Robotics and autonomous systems , Vol. 57 ( 2009 ), 469--483. Brenna D Argall, Sonia Chernova, Manuela Veloso, and Brett Browning. 2009. A survey of robot learning from demonstration. Robotics and autonomous systems , Vol. 57 (2009), 469--483."},{"key":"e_1_3_2_2_2_1","first-page":"103500","article-title":"A survey of inverse reinforcement learning: Challenges, methods and progress","volume":"297","author":"Arora Saurabh","year":"2021","unstructured":"Saurabh Arora and Prashant Doshi . 2021 . A survey of inverse reinforcement learning: Challenges, methods and progress . AI , Vol. 297 (2021), 103500 . Saurabh Arora and Prashant Doshi. 2021. A survey of inverse reinforcement learning: Challenges, methods and progress. AI , Vol. 297 (2021), 103500.","journal-title":"AI"},{"key":"e_1_3_2_2_3_1","unstructured":"Keping Bi Qingyao Ai Yongfeng Zhang and W Bruce Croft. 2019. Conversational product search based on negative feedback. In CIKM. 359--368. Keping Bi Qingyao Ai Yongfeng Zhang and W Bruce Croft. 2019. Conversational product search based on negative feedback. In CIKM. 359--368."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"crossref","unstructured":"Senthilkumar Chandramohan Matthieu Geist Fabrice Lefevre and Olivier Pietquin. 2011. User simulation in dialogue systems using inverse reinforcement learning. In Interspeech 2011 . 1025--1028. Senthilkumar Chandramohan Matthieu Geist Fabrice Lefevre and Olivier Pietquin. 2011. User simulation in dialogue systems using inverse reinforcement learning. In Interspeech 2011 . 1025--1028.","DOI":"10.21437\/Interspeech.2011-302"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013312"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"crossref","unstructured":"Qibin Chen Junyang Lin Yichang Zhang Ming Ding Yukuo Cen Hongxia Yang and Jie Tang. 2019 b. Towards Knowledge-Based Recommender Dialog System. In EMNLP-IJCNLP. 1803--1813. Qibin Chen Junyang Lin Yichang Zhang Ming Ding Yukuo Cen Hongxia Yang and Jie Tang. 2019 b. Towards Knowledge-Based Recommender Dialog System. In EMNLP-IJCNLP. 1803--1813.","DOI":"10.18653\/v1\/D19-1189"},{"key":"e_1_3_2_2_7_1","volume-title":"H Chi","author":"Christakopoulou Konstantina","year":"2018","unstructured":"Konstantina Christakopoulou , Alex Beutel , Rui Li , Sagar Jain , and Ed H Chi . 2018 . Q&R: A Two-Stage Approach toward Interactive Recommendation. In SIGKDD . 139--148. Konstantina Christakopoulou, Alex Beutel, Rui Li, Sagar Jain, and Ed H Chi. 2018. Q&R: A Two-Stage Approach toward Interactive Recommendation. In SIGKDD . 139--148."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"crossref","unstructured":"Konstantina Christakopoulou Filip Radlinski and Katja Hofmann. 2016. Towards conversational recommender systems. In SIGKDD. 815--824. Konstantina Christakopoulou Filip Radlinski and Katja Hofmann. 2016. Towards conversational recommender systems. In SIGKDD. 815--824.","DOI":"10.1145\/2939672.2939746"},{"key":"e_1_3_2_2_9_1","unstructured":"Paul F. Christiano Jan Leike Tom B. Brown Miljan Martic Shane Legg and Dario Amodei. 2017. Deep Reinforcement Learning from Human Preferences. In NeurIPS . 4299--4307. Paul F. Christiano Jan Leike Tom B. Brown Miljan Martic Shane Legg and Dario Amodei. 2017. Deep Reinforcement Learning from Human Preferences. In NeurIPS . 4299--4307."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"crossref","unstructured":"Yang Deng Yaliang Li Fei Sun Bolin Ding and Wai Lam. 2021. Unified Conversational Recommendation Policy Learning via Graph-based Reinforcement Learning. In SIGIR. 1431--1441. Yang Deng Yaliang Li Fei Sun Bolin Ding and Wai Lam. 2021. Unified Conversational Recommendation Policy Learning via Graph-based Reinforcement Learning. In SIGIR. 1431--1441.","DOI":"10.1145\/3404835.3462913"},{"key":"e_1_3_2_2_11_1","unstructured":"Justin Fu Katie Luo and Sergey Levine. 2018. Learning Robust Rewards with Adverserial Inverse Reinforcement Learning. In ICLR . Justin Fu Katie Luo and Sergey Levine. 2018. Learning Robust Rewards with Adverserial Inverse Reinforcement Learning. In ICLR ."},{"key":"e_1_3_2_2_12_1","volume-title":"Advances and challenges in conversational recommender systems: A survey. arXiv preprint arXiv:2101.09459","author":"Gao Chongming","year":"2021","unstructured":"Chongming Gao , Wenqiang Lei , Xiangnan He , Maarten de Rijke , and Tat-Seng Chua . 2021. Advances and challenges in conversational recommender systems: A survey. arXiv preprint arXiv:2101.09459 ( 2021 ). Chongming Gao, Wenqiang Lei, Xiangnan He, Maarten de Rijke, and Tat-Seng Chua. 2021. Advances and challenges in conversational recommender systems: A survey. arXiv preprint arXiv:2101.09459 (2021)."},{"key":"e_1_3_2_2_13_1","first-page":"4565","article-title":"Generative adversarial imitation learning","volume":"29","author":"Ho Jonathan","year":"2016","unstructured":"Jonathan Ho and Stefano Ermon . 2016 . Generative adversarial imitation learning . NIPS , Vol. 29 (2016), 4565 -- 4573 . Jonathan Ho and Stefano Ermon. 2016. Generative adversarial imitation learning. NIPS , Vol. 29 (2016), 4565--4573.","journal-title":"NIPS"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3453154"},{"key":"e_1_3_2_2_15_1","volume-title":"Kingma and Jimmy Ba","author":"Diederik","year":"2015","unstructured":"Diederik P. Kingma and Jimmy Ba . 2015 . Adam : A Method for Stochastic Optimization. In ICLR . Diederik P. Kingma and Jimmy Ba. 2015. Adam: A Method for Stochastic Optimization. In ICLR ."},{"key":"e_1_3_2_2_16_1","volume-title":"Kipf and Max Welling","author":"Thomas","year":"2017","unstructured":"Thomas N. Kipf and Max Welling . 2017 . Semi-Supervised Classification with Graph Convolutional Networks. In ICLR . Thomas N. Kipf and Max Welling. 2017. Semi-Supervised Classification with Graph Convolutional Networks. In ICLR ."},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"crossref","unstructured":"Wenqiang Lei Xiangnan He Maarten de Rijke and Tat-Seng Chua. 2020 a. Conversational recommendation: Formulation methods and evaluation. In SIGIR . 2425--2428. Wenqiang Lei Xiangnan He Maarten de Rijke and Tat-Seng Chua. 2020 a. Conversational recommendation: Formulation methods and evaluation. In SIGIR . 2425--2428.","DOI":"10.1145\/3397271.3401419"},{"key":"e_1_3_2_2_18_1","unstructured":"Wenqiang Lei Xiangnan He Yisong Miao Qingyun Wu Richang Hong Min-Yen Kan and Tat-Seng Chua. 2020 b. Estimation--Action--Reflection: Towards Deep Interaction Between Conversational and Recommender Systems. In WSDM. 304--312. Wenqiang Lei Xiangnan He Yisong Miao Qingyun Wu Richang Hong Min-Yen Kan and Tat-Seng Chua. 2020 b. Estimation--Action--Reflection: Towards Deep Interaction Between Conversational and Recommender Systems. In WSDM. 304--312."},{"key":"e_1_3_2_2_19_1","unstructured":"Wenqiang Lei Gangyi Zhang Xiangnan He Yisong Miao Xiang Wang Liang Chen and Tat-Seng Chua. 2020 c. Interactive path reasoning on graph for conversational recommendation. In SIGKDD . 2073--2083. Wenqiang Lei Gangyi Zhang Xiangnan He Yisong Miao Xiang Wang Liang Chen and Tat-Seng Chua. 2020 c. Interactive path reasoning on graph for conversational recommendation. In SIGKDD . 2073--2083."},{"key":"e_1_3_2_2_20_1","volume-title":"Hannes Schulz, Vincent Michalski, Laurent Charlin, and Chris Pal.","author":"Li Raymond","year":"2018","unstructured":"Raymond Li , Samira Ebrahimi Kahou , Hannes Schulz, Vincent Michalski, Laurent Charlin, and Chris Pal. 2018 . Towards Deep Conversational Recommendations. In NeurIPS. 9748--9758. Raymond Li, Samira Ebrahimi Kahou, Hannes Schulz, Vincent Michalski, Laurent Charlin, and Chris Pal. 2018. Towards Deep Conversational Recommendations. In NeurIPS. 9748--9758."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3446427","article-title":"Seamlessly unifying attributes and items: Conversational recommendation for cold-start users","volume":"39","author":"Li Shijun","year":"2021","unstructured":"Shijun Li , Wenqiang Lei , Qingyun Wu , Xiangnan He , Peng Jiang , and Tat-Seng Chua . 2021 . Seamlessly unifying attributes and items: Conversational recommendation for cold-start users . TOIS , Vol. 39 (2021), 1 -- 29 . Shijun Li, Wenqiang Lei, Qingyun Wu, Xiangnan He, Peng Jiang, and Tat-Seng Chua. 2021. Seamlessly unifying attributes and items: Conversational recommendation for cold-start users. TOIS , Vol. 39 (2021), 1--29.","journal-title":"TOIS"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"crossref","unstructured":"Lizi Liao Yunshan Ma Xiangnan He Richang Hong and Tat-Seng Chua. 2018. Knowledge-aware Multimodal Dialogue Systems. In ACM MM. 801--809. Lizi Liao Yunshan Ma Xiangnan He Richang Hong and Tat-Seng Chua. 2018. Knowledge-aware Multimodal Dialogue Systems. In ACM MM. 801--809.","DOI":"10.1145\/3240508.3240605"},{"key":"e_1_3_2_2_23_1","unstructured":"Zeming Liu Haifeng Wang Zheng-Yu Niu Hua Wu Wanxiang Che and Ting Liu. 2020. Towards Conversational Recommendation over Multi-Type Dialogs. In ACL . 1036--1049. Zeming Liu Haifeng Wang Zheng-Yu Niu Hua Wu Wanxiang Che and Ting Liu. 2020. Towards Conversational Recommendation over Multi-Type Dialogs. In ACL . 1036--1049."},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"crossref","unstructured":"Volodymyr Mnih Koray Kavukcuoglu David Silver Andrei A. Rusu Joel Veness Marc G. Bellemare Alex Graves Martin A. Riedmiller Andreas Fidjeland Georg Ostrovski Stig Petersen Charles Beattie Amir Sadik Ioannis Antonoglou Helen King Dharshan Kumaran Daan Wierstra Shane Legg and Demis Hassabis. 2015. Human-level control through deep reinforcement learning. Nat. (2015) 529--533. Volodymyr Mnih Koray Kavukcuoglu David Silver Andrei A. Rusu Joel Veness Marc G. Bellemare Alex Graves Martin A. Riedmiller Andreas Fidjeland Georg Ostrovski Stig Petersen Charles Beattie Amir Sadik Ioannis Antonoglou Helen King Dharshan Kumaran Daan Wierstra Shane Legg and Demis Hassabis. 2015. Human-level control through deep reinforcement learning. Nat. (2015) 529--533.","DOI":"10.1038\/nature14236"},{"key":"e_1_3_2_2_25_1","volume-title":"Russell","author":"Ng Andrew Y.","year":"2000","unstructured":"Andrew Y. Ng and Stuart J . Russell . 2000 . Algorithms for Inverse Reinforcement Learning. In ICML. 663--670. Andrew Y. Ng and Stuart J. Russell. 2000. Algorithms for Inverse Reinforcement Learning. In ICML. 663--670."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"crossref","unstructured":"Xuhui Ren Hongzhi Yin Tong Chen Hao Wang Zi Huang and Kai Zheng. 2021. Learning to ask appropriate questions in conversational recommendation. In SIGIR . 808--817. Xuhui Ren Hongzhi Yin Tong Chen Hao Wang Zi Huang and Kai Zheng. 2021. Learning to ask appropriate questions in conversational recommendation. In SIGIR . 808--817.","DOI":"10.1145\/3404835.3462839"},{"key":"e_1_3_2_2_27_1","volume-title":"BPR: Bayesian personalized ranking from implicit feedback. In UAI. 452--461.","author":"Rendle Steffen","year":"2009","unstructured":"Steffen Rendle , Christoph Freudenthaler , Zeno Gantner , and Lars Schmidt-Thieme . 2009 . BPR: Bayesian personalized ranking from implicit feedback. In UAI. 452--461. Steffen Rendle, Christoph Freudenthaler, Zeno Gantner, and Lars Schmidt-Thieme. 2009. BPR: Bayesian personalized ranking from implicit feedback. In UAI. 452--461."},{"key":"e_1_3_2_2_28_1","unstructured":"Yueming Sun and Yi Zhang. 2018. Conversational Recommender System. In SIGIR. 235--244. Yueming Sun and Yi Zhang. 2018. Conversational Recommender System. In SIGIR. 235--244."},{"key":"e_1_3_2_2_29_1","unstructured":"Richard S. Sutton David A. McAllester Satinder P. Singh and Yishay Mansour. 1999. Policy Gradient Methods for Reinforcement Learning with Function Approximation. In NeurIPS . 1057--1063. Richard S. Sutton David A. McAllester Satinder P. Singh and Yishay Mansour. 1999. Policy Gradient Methods for Reinforcement Learning with Function Approximation. In NeurIPS . 1057--1063."},{"key":"e_1_3_2_2_30_1","unstructured":"Kerui Xu Jingxuan Yang Jun Xu Sheng Gao Jun Guo and Ji-Rong Wen. 2021. Adapting User Preference to Online Feedback in Multi-round Conversational Recommendation. In WSDM. 364--372. Kerui Xu Jingxuan Yang Jun Xu Sheng Gao Jun Guo and Ji-Rong Wen. 2021. Adapting User Preference to Online Feedback in Multi-round Conversational Recommendation. In WSDM. 364--372."},{"key":"e_1_3_2_2_31_1","unstructured":"Tong Yu Yilin Shen and Hongxia Jin. 2019. An Visual Dialog Augmented Interactive Recommender System. In SIGKDD. 157--165. Tong Yu Yilin Shen and Hongxia Jin. 2019. An Visual Dialog Augmented Interactive Recommender System. In SIGKDD. 157--165."},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"crossref","unstructured":"Xiaoying Zhang Hong Xie Hang Li and John CS Lui. 2020. Conversational contextual bandit: Algorithm and application. In WWW. 662--672. Xiaoying Zhang Hong Xie Hang Li and John CS Lui. 2020. Conversational contextual bandit: Algorithm and application. In WWW. 662--672.","DOI":"10.1145\/3366423.3380148"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"crossref","unstructured":"Yongfeng Zhang Xu Chen Qingyao Ai Liu Yang and W Bruce Croft. 2018. Towards conversational search and recommendation: System ask user respond. In CIKM . 177--186. Yongfeng Zhang Xu Chen Qingyao Ai Liu Yang and W Bruce Croft. 2018. Towards conversational search and recommendation: System ask user respond. In CIKM . 177--186.","DOI":"10.1145\/3269206.3271776"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"crossref","unstructured":"Xiangyu Zhao Liang Zhang Zhuoye Ding Long Xia Jiliang Tang and Dawei Yin. 2018. Recommendations with Negative Feedback via Pairwise Deep Reinforcement Learning. In SIGKDD . 1040--1048. Xiangyu Zhao Liang Zhang Zhuoye Ding Long Xia Jiliang Tang and Dawei Yin. 2018. Recommendations with Negative Feedback via Pairwise Deep Reinforcement Learning. In SIGKDD . 1040--1048.","DOI":"10.1145\/3219819.3219886"},{"key":"e_1_3_2_2_35_1","volume-title":"Xing Xie, and Zhenhui Li.","author":"Zheng Guanjie","year":"2018","unstructured":"Guanjie Zheng , Fuzheng Zhang , Zihan Zheng , Yang Xiang , Nicholas Jing Yuan , Xing Xie, and Zhenhui Li. 2018 . DRN : A Deep Reinforcement Learning Framework for News Recommendation. In WWW . 167--176. Guanjie Zheng, Fuzheng Zhang, Zihan Zheng, Yang Xiang, Nicholas Jing Yuan, Xing Xie, and Zhenhui Li. 2018. DRN: A Deep Reinforcement Learning Framework for News Recommendation. In WWW . 167--176."},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"crossref","unstructured":"Kun Zhou Wayne Xin Zhao Shuqing Bian Yuanhang Zhou Ji-Rong Wen and Jingsong Yu. 2020 a. Improving conversational recommender systems via knowledge graph based semantic fusion. In SIGKDD. 1006--1014. Kun Zhou Wayne Xin Zhao Shuqing Bian Yuanhang Zhou Ji-Rong Wen and Jingsong Yu. 2020 a. Improving conversational recommender systems via knowledge graph based semantic fusion. In SIGKDD. 1006--1014.","DOI":"10.1145\/3394486.3403143"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"crossref","unstructured":"Kun Zhou Yuanhang Zhou Wayne Xin Zhao Xiaoke Wang and Ji-Rong Wen. 2020 b. Towards Topic-Guided Conversational Recommender System. In COLING. 4128--4139. Kun Zhou Yuanhang Zhou Wayne Xin Zhao Xiaoke Wang and Ji-Rong Wen. 2020 b. Towards Topic-Guided Conversational Recommender System. In COLING. 4128--4139.","DOI":"10.18653\/v1\/2020.coling-main.365"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"crossref","unstructured":"Jie Zou Yifan Chen and Evangelos Kanoulas. 2020. Towards question-based recommender systems. In SIGIR. 881--890. Jie Zou Yifan Chen and Evangelos Kanoulas. 2020. Towards question-based recommender systems. In SIGIR. 881--890.","DOI":"10.1145\/3397271.3401180"}],"event":{"name":"SIGIR '22: The 45th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Madrid Spain","acronym":"SIGIR '22","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3477495.3531844","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3477495.3531844","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T18:10:26Z","timestamp":1750183826000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3477495.3531844"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,6]]},"references-count":38,"alternative-id":["10.1145\/3477495.3531844","10.1145\/3477495"],"URL":"https:\/\/doi.org\/10.1145\/3477495.3531844","relation":{},"subject":[],"published":{"date-parts":[[2022,7,6]]},"assertion":[{"value":"2022-07-07","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}