{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T15:58:40Z","timestamp":1772553520478,"version":"3.50.1"},"reference-count":60,"publisher":"Association for Computing Machinery (ACM)","issue":"3","license":[{"start":{"date-parts":[[2020,6,5]],"date-time":"2020-06-05T00:00:00Z","timestamp":1591315200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Beijing Academy of Artificial Intelligence","award":["No. BAAI2019ZD0306"],"award-info":[{"award-number":["No. BAAI2019ZD0306"]}]},{"DOI":"10.13039\/501100001809","name":"the National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["No. 61425016, 61722211, 61773362, 61872338 and 61902381"],"award-info":[{"award-number":["No. 61425016, 61722211, 61773362, 61872338 and 61902381"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"the Youth Innovation Promotion Association CAS","award":["No. 20144310, and 2016102"],"award-info":[{"award-number":["No. 20144310, and 2016102"]}]},{"name":"the Lenovo-CAS Joint Lab Youth Scientist Project"},{"name":"the Foundation and Frontier Research Key Program of Chongqing Science and Technology Commission","award":["No. cstc2017jcyjBX0059"],"award-info":[{"award-number":["No. cstc2017jcyjBX0059"]}]},{"name":"the National Key RD Program of China","award":["No. 2016QY02D0405"],"award-info":[{"award-number":["No. 2016QY02D0405"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Inf. Syst."],"published-print":{"date-parts":[[2020,7,31]]},"abstract":"<jats:p>The conversation task is usually formulated as a conditional generation problem, i.e., to generate a natural and meaningful response given the input utterance. Generally speaking, this formulation is apparently based on an oversimplified assumption that the response is solely dependent on the input utterance. It ignores the subjective factor of the responder, e.g., his\/her emotion or knowledge state, which is a major factor that affects the response in practice. Without explicitly differentiating such subjective factor behind the response, existing generation models can only learn the general shape of conversations, leading to the blandness problem of the response. Moreover, there is no intervention mechanism within the existing generation process, since the response is fully decided by the input utterance. In this work, we propose to view the conversation task as a dual-factor generation problem, including an objective factor denoting the input utterance and a subjective factor denoting the responder state. We extend the existing neural sequence-to-sequence (Seq2Seq) model to accommodate the responder state modeling. We introduce two types of responder state, i.e., discrete and continuous state, to model emotion state and topic preference state, respectively. We show that with our dual-factor generation model, we can not only better fit the conversation data, but also actively control the generation of the response with respect to sentiment or topic specificity.<\/jats:p>","DOI":"10.1145\/3394052","type":"journal-article","created":{"date-parts":[[2020,6,5]],"date-time":"2020-06-05T10:09:37Z","timestamp":1591351777000},"page":"1-31","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["Dual-factor Generation Model for Conversation"],"prefix":"10.1145","volume":"38","author":[{"given":"Ruqing","family":"Zhang","sequence":"first","affiliation":[{"name":"University of Chinese Academy of Sciences, Beijing, China; CAS Key Lab of Network Data Science and Technology, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1086-0202","authenticated-orcid":false,"given":"Jiafeng","family":"Guo","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences, Beijing, China; CAS Key Lab of Network Data Science and Technology, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yixing","family":"Fan","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences, Beijing, China; CAS Key Lab of Network Data Science and Technology, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanyan","family":"Lan","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences, Beijing, China; CAS Key Lab of Network Data Science and Technology, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xueqi","family":"Cheng","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences, Beijing, China; CAS Key Lab of Network Data Science and Technology, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2020,6,5]]},"reference":[{"key":"e_1_2_1_1_1","volume-title":"Conversational contextual cues: The case of personalization and history for response ranking. arXiv preprint arXiv:1606.00372","author":"Al-Rfou Rami","year":"2016"},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-76941-7_12"},{"key":"e_1_2_1_3_1","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR\u201915)","author":"Bahdanau Dzmitry","year":"2015"},{"key":"e_1_2_1_4_1","volume-title":"Learning end-to-end goal-oriented dialog. arXiv preprint arXiv:1605.07683","author":"Bordes Antoine","year":"2016"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32233-5_10"},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"e_1_2_1_7_1","volume-title":"Towards end-to-end reinforcement learning of dialogue agents for information access. arXiv preprint arXiv:1609.00777","author":"Dhingra Bhuwan","year":"2016"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1177\/001316447303300309"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1561\/1500000074"},{"key":"e_1_2_1_10_1","volume-title":"Proceedings of the 54th Meeting of the Association for Computational Linguistics. Association for Computational Linguistics.","author":"Gu Jiatao"},{"key":"e_1_2_1_11_1","volume-title":"Proceedings of the 15th Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL\u201914)","author":"Henderson Matthew"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2008"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2005.01.012"},{"key":"e_1_2_1_14_1","volume-title":"An information retrieval approach to short text conversation. arXiv preprint arXiv:1408.6988","author":"Ji Zongcheng","year":"2014"},{"key":"e_1_2_1_15_1","unstructured":"Michael Kearns. 2000. Cobot in LambdaMOO: A social statistics agent. In AAAI\/IAAI.  Michael Kearns. 2000. Cobot in LambdaMOO: A social statistics agent. In AAAI\/IAAI."},{"key":"e_1_2_1_16_1","volume-title":"Proceedings of the International Conference on Learning Representations.","author":"Kingma Diederik","year":"2015"},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1014"},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1094"},{"key":"e_1_2_1_19_1","volume-title":"Data distillation for controlling specificity in dialogue generation. arXiv preprint arXiv:1702.06703","author":"Li Jiwei","year":"2017"},{"key":"e_1_2_1_20_1","volume-title":"Deep reinforcement learning for dialogue generation. arXiv preprint arXiv:1606.01541","author":"Li Jiwei","year":"2016"},{"key":"e_1_2_1_21_1","volume-title":"Adversarial learning for neural dialogue generation. arXiv preprint arXiv:1701.06547","author":"Li Jiwei","year":"2017"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.3115\/1073445.1073465"},{"key":"e_1_2_1_23_1","first-page":"1","article-title":"An emotion-based responding model for natural language conversation","volume":"9","author":"Liu Feng","year":"2018","journal-title":"World Wide Web-internet Web Inf. Syst."},{"key":"e_1_2_1_24_1","volume-title":"Multi-task learning for speaker-role adaptation in neural conversation models. arXiv preprint arXiv:1710.07388","author":"Luan Yi","year":"2017"},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016794"},{"key":"e_1_2_1_26_1","first-page":"2579","article-title":"Visualizing data using t-SNE","author":"van der Maaten Laurens","year":"2008","journal-title":"J. Mach. Learn. Res. 9"},{"key":"e_1_2_1_27_1","volume-title":"Proceedings of the 40th International ACM SIGIR Conference.","author":"Min Yang","year":"2017"},{"key":"e_1_2_1_28_1","volume-title":"Proceedings of the International Conference on Computational Linguistics (COLING\u201916)","author":"Mou Lili","year":"2016"},{"key":"e_1_2_1_29_1","volume-title":"Proceedings of the 40th Meeting on Association for Computational Linguistics. Association for Computational Linguistics, 311\u2013318","author":"Papineni Kishore","year":"2002"},{"key":"e_1_2_1_30_1","doi-asserted-by":"crossref","unstructured":"Diana Perez-Marin. 2011. Conversational Agents and Natural Language Interaction: Techniques and Effective Practices: Techniques and Effective Practices. IGI Global.  Diana Perez-Marin. 2011. Conversational Agents and Natural Language Interaction: Techniques and Effective Practices: Techniques and Effective Practices. IGI Global.","DOI":"10.4018\/978-1-60960-617-6"},{"key":"e_1_2_1_31_1","volume-title":"Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI\u201918)","author":"Qiao Qian","year":"2018"},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-2079"},{"key":"e_1_2_1_33_1","volume-title":"Proceedings of the Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, 583\u2013593","author":"Ritter Alan"},{"key":"e_1_2_1_34_1","volume-title":"Robertson and Steve Walker","author":"Stephen","year":"1994"},{"key":"e_1_2_1_35_1","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence (AAAI\u201916)","author":"Serban Iulian Vlad","year":"2016"},{"key":"e_1_2_1_36_1","volume-title":"Proceedings of the 31st AAAI Conference on Artificial Intelligence.","author":"Serban Iulian Vlad","year":"2017"},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-1152"},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-2080"},{"key":"e_1_2_1_39_1","volume-title":"A neural network approach to context-sensitive generation of conversational responses. arXiv preprint arXiv:1506.06714","author":"Sordoni Alessandro","year":"2015"},{"key":"e_1_2_1_40_1","volume-title":"Proceedings of the International Conference on Neural Information Processing Systems (NIPS\u201914)","author":"Sutskever Ilya","year":"2014"},{"key":"e_1_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-2036"},{"key":"e_1_2_1_42_1","volume-title":"A neural conversational model. arXiv preprint arXiv:1506.05869","author":"Vinyals Oriol","year":"2015"},{"key":"e_1_2_1_43_1","volume-title":"Proceedings of the 39th Meeting on Association for Computational Linguistics. Association for Computational Linguistics, 515\u2013522","author":"Walker Marilyn A."},{"key":"e_1_2_1_44_1","volume-title":"Proceedings of the Conference on Empirical Methods in Natural Language Processing.","author":"Wang Hao","year":"2013"},{"key":"e_1_2_1_45_1","volume-title":"Proceedings of the SIGDIAL Conference. 404\u2013413","author":"Williams Jason","year":"2013"},{"key":"e_1_2_1_46_1","volume-title":"Sequential matching network: A new architecture for multi-turn response selection in retrieval-based chatbots. arXiv preprint arXiv:1612.01627","author":"Wu Yu","year":"2016"},{"key":"e_1_2_1_47_1","volume-title":"Proceedings of the AAAI. 3351\u20133357","author":"Xing Chen","year":"2017"},{"key":"e_1_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/2911451.2911542"},{"key":"e_1_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/2983323.2983360"},{"key":"e_1_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080843"},{"key":"e_1_2_1_51_1","volume-title":"A hybrid retrieval-generation neural conversation model. arXiv preprint arXiv:1904.09068","author":"Yang Liu","year":"2019"},{"key":"e_1_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210011"},{"key":"e_1_2_1_53_1","volume-title":"An attentional neural conversation model with improved specificity. arXiv preprint arXiv:1606.01292","author":"Yao Kaisheng","year":"2016"},{"key":"e_1_2_1_54_1","volume-title":"Proceedings of the 31st AAAI Conference on Artificial Intelligence.","author":"Yu Lantao","year":"2017"},{"key":"e_1_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1102"},{"key":"e_1_2_1_56_1","first-page":"1","article-title":"Neural personalized response generation as domain adaptation","volume":"4","author":"Zhang Wei Nan","year":"2017","journal-title":"World Wide Web-internet Web Inf. Syst."},{"key":"e_1_2_1_57_1","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence (AAAI\u201917)","author":"Zhou Ganbin","year":"2017"},{"key":"e_1_2_1_58_1","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence (AAAI\u201918)","author":"Zhou Hao","year":"2018"},{"key":"e_1_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1036"},{"key":"e_1_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1104"}],"container-title":["ACM Transactions on Information Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3394052","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3394052","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:47:12Z","timestamp":1750193232000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3394052"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,6,5]]},"references-count":60,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2020,7,31]]}},"alternative-id":["10.1145\/3394052"],"URL":"https:\/\/doi.org\/10.1145\/3394052","relation":{},"ISSN":["1046-8188","1558-2868"],"issn-type":[{"value":"1046-8188","type":"print"},{"value":"1558-2868","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,6,5]]},"assertion":[{"value":"2019-10-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2020-04-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2020-06-05","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}