{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T01:54:50Z","timestamp":1784426090515,"version":"3.55.0"},"reference-count":75,"publisher":"Association for Computing Machinery (ACM)","issue":"5","license":[{"start":{"date-parts":[[2024,4,27]],"date-time":"2024-04-27T00:00:00Z","timestamp":1714176000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Research Grants Council of Hong Kong","award":["15207122, 15207920, 15207821, 15204018, 15213323"],"award-info":[{"award-number":["15207122, 15207920, 15207821, 15204018, 15213323"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62076212"],"award-info":[{"award-number":["62076212"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"PolyU internal","award":["ZVQ0, ZVVX"],"award-info":[{"award-number":["ZVQ0, ZVVX"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Inf. Syst."],"published-print":{"date-parts":[[2024,9,30]]},"abstract":"<jats:p>Target-oriented proactive dialogue systems aim at leading conversations from a dialogue context toward a pre-determined target, such as making recommendations on designated items or introducing new specific topics. To this end, it is critical for such dialogue systems to plan reasonable actions to drive the conversation proactively, and meanwhile, to plan appropriate topics to move the conversation forward to the target topic smoothly. In this work, we mainly focus on effective dialogue planning for target-oriented dialogue generation. Inspired by decision-making theories in cognitive science, we propose a novel target-constrained bidirectional planning (TRIP) approach, which plans an appropriate dialogue path by looking ahead and looking back. By formulating the planning as a generation task, our TRIP bidirectionally generates a dialogue path consisting of a sequence of &lt;action, topic&gt; pairs using two Transformer decoders. They are expected to supervise each other and converge on consistent actions and topics by minimizing the decision gap and contrastive generation of targets. Moreover, we propose a target-constrained decoding algorithm with a bidirectional agreement to better control the planning process. Subsequently, we adopt the planned dialogue paths to guide dialogue generation in a pipeline manner, where we explore two variants: prompt-based generation and plan-controlled generation. Extensive experiments are conducted on two challenging dialogue datasets, which are re-purposed for exploring target-oriented dialogue. Our automatic and human evaluations demonstrate that the proposed methods significantly outperform various baseline models.<\/jats:p>","DOI":"10.1145\/3652598","type":"journal-article","created":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T11:52:55Z","timestamp":1710330775000},"page":"1-27","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Target-constrained Bidirectional Planning for Generation of Target-oriented Proactive Dialogue"],"prefix":"10.1145","volume":"42","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8992-8336","authenticated-orcid":false,"given":"Jian","family":"Wang","sequence":"first","affiliation":[{"name":"The Hong Kong Polytechnic University, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8846-8622","authenticated-orcid":false,"given":"Dongding","family":"Lin","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University, Hong Kong China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7360-8864","authenticated-orcid":false,"given":"Wenjie","family":"Li","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University, Hong Kong China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,4,27]]},"reference":[{"key":"e_1_3_2_2_2","volume-title":"Proceedings of the International Conference on Learning Representations.","author":"Dathathri Sumanth","year":"2020","unstructured":"Sumanth Dathathri, Andrea Madotto, Janice Lan, Jane Hung, Eric Frank, Piero Molino, Jason Yosinski, and Rosanne Liu. 2020. Plug and play language models: A simple approach to controlled text generation. In Proceedings of the International Conference on Learning Representations."},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/738"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/3570640"},{"key":"e_1_3_2_5_2","first-page":"4171","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics, Minneapolis, Minnesota, 4171\u20134186."},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1037\/h0031619"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-demos.4"},{"key":"e_1_3_2_8_2","unstructured":"Ana Valeria Gonzalez Isabelle Augenstein and Anders S\u00f8gaard. 2019. Retrieval-based goal-oriented dialogue generation. arXiv:1909.13717. Retrieved from https:\/\/arxiv.org\/abs\/1909.13717"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-naacl.97"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.654"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.163"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.501"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1055"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.57"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41593-021-00866-w"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1203"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1181"},{"key":"e_1_3_2_18_2","unstructured":"Diederik P. Kingma and Jimmy Ba. 2015. Adam: A method for stochastic optimization. In The International Conference for Learning Representations (ICLR)."},{"key":"e_1_3_2_19_2","unstructured":"Seanie Lee Dong Bok Lee and Sung Ju Hwang. 2021. Contrastive learning with adversarial perturbations for conditional text generation. In The International Conference for Learning Representations (ICLR)."},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/3336191.3371769"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1014"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.5555\/3327546.3327641"},{"key":"e_1_3_2_24_2","unstructured":"Yu Li Shirley Anugrah Hayati Weiyan Shi and Zhou Yu. 2021. DEUX: An attribute-guided framework for sociable recommendation dialog systems. arXiv:2105.00825. Retrieved from https:\/\/arxiv.org\/abs\/2105.00825"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.617"},{"key":"e_1_3_2_26_2","volume-title":"Proceedings of the 3rd Edition of Knowledge-aware and Conversational Recommender Systems & 5th Edition of Recommendation in Complex Environments Joint Workshop @ RecSys 2021","author":"Lin Dongding","year":"2021","unstructured":"Dongding Lin, Jian Wang, and Wenjie Li. 2021. Target-guided knowledge-aware recommendation dialogue system: An empirical investigation. In Proceedings of the 3rd Edition of Knowledge-aware and Conversational Recommender Systems & 5th Edition of Recommendation in Complex Environments Joint Workshop @ RecSys 2021."},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i4.25567"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00390"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.356"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.98"},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.139"},{"key":"e_1_3_2_32_2","unstructured":"Andrea Madotto Zhaojiang Lin Genta Indra Winata and Pascale Fung. 2021. Few-shot bot: Prompt-based learning for dialogue systems. arXiv:2110.08118. Retrieved from https:\/\/arxiv.org\/abs\/2110.08118"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1136"},{"key":"e_1_3_2_34_2","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","author":"Moryossef Amit","year":"2019","unstructured":"Amit Moryossef, Yoav Goldberg, and Ido Dagan. 2019. Step-by-Step: Separating planning from realization in neural data-to-text generation. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2267\u20132277."},{"key":"e_1_3_2_35_2","volume-title":"ICML","author":"Nair Vinod","year":"2010","unstructured":"Vinod Nair and Geoffrey E. Hinton. 2010. Rectified linear units improve restricted boltzmann machines. In ICML."},{"key":"e_1_3_2_36_2","article-title":"Introducing ChatGPT","year":"2022","unstructured":"OpenAI. 2022. Introducing ChatGPT. Retrieved November 30, 2022 from https:\/\/openai.com\/blog\/chatgpt","journal-title":"Retrieved November 30, 2022"},{"key":"e_1_3_2_37_2","first-page":"311","volume-title":"Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics","author":"Papineni Kishore","year":"2002","unstructured":"Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. Bleu: A method for automatic evaluation of machine translation. In Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Philadelphia, Pennsylvania, USA, 311\u2013318."},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1119"},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016908"},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6390"},{"issue":"8","key":"e_1_3_2_41_2","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","year":"2019","unstructured":"Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, and Ilya Sutskever. 2019. Language models are unsupervised multitask learners. OpenAI Blog 1, 8 (2019), 9.","journal-title":"OpenAI Blog"},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.194"},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1948.tb01338.x"},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1321"},{"key":"e_1_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-naacl.181"},{"key":"e_1_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.76"},{"key":"e_1_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210002"},{"key":"e_1_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1565"},{"key":"e_1_3_2_49_2","unstructured":"Hugo Touvron Thibaut Lavril Gautier Izacard Xavier Martinet Marie-Anne Lachaux Timoth\u00e9e Lacroix Baptiste Rozi\u00e8re Naman Goyal Eric Hambro Faisal Azhar Aurelien Rodriguez Armand Joulin Edouard Grave and Guillaume Lample. 2023. Llama: Open and efficient foundation language models. arXiv:2302.13971. Retrieved from https:\/\/arxiv.org\/abs\/2302.13971"},{"key":"e_1_3_2_50_2","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale Dan Bikel Lukas Blecher Cristian Canton Ferrer Moya Chen Guillem Cucurull David Esiobu Jude Fernandes Jeremy Fu Wenyin Fu Brian Fuller Cynthia Gao Vedanuj Goswami Naman Goyal Anthony Hartshorn Saghar Hosseini Rui Hou Hakan Inan Marcin Kardas Viktor Kerkez Madian Khabsa Isabel Kloumann Artem Korenev Punit Singh Koura Marie-Anne Lachaux Thibaut Lavril Jenya Lee Diana Liskovich Yinghai Lu Yuning Mao Xavier Martinet Todor Mihaylov Pushkar Mishra Igor Molybog Yixin Nie Andrew Poulton Jeremy Reizenstein Rashi Rungta Kalyan Saladi Alan Schelten Ruan Silva Eric Michael Smith Ranjan Subramanian Xiaoqing Ellen Tan Binh Tang Ross Taylor Adina Williams Jian Xiang Kuan Puxin Xu Zheng Yan Iliyan Zarov Yuchen Zhang Angela Fan Melanie Kambadur Sharan Narang Aurelien Rodriguez Robert Stojnic Sergey Edunov and Thomas Scialom. 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv:2307.09288. Retrieved from https:\/\/arxiv.org\/abs\/2307.09288"},{"key":"e_1_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4757-3157-6_2"},{"key":"e_1_3_2_52_2","volume-title":"Proceedings of the NeurIPS 2022 Foundation Models for Decision Making Workshop","author":"Valmeekam Karthik","year":"2022","unstructured":"Karthik Valmeekam, Alberto Olmo, Sarath Sreedharan, and Subbarao Kambhampati. 2022. Large language models still can\u2019t plan (a benchmark for llms on planning and reasoning about change). In Proceedings of the NeurIPS 2022 Foundation Models for Decision Making Workshop."},{"key":"e_1_3_2_53_2","unstructured":"Karthik Valmeekam Sarath Sreedharan Matthew Marquez Alberto Olmo and Subbarao Kambhampati. 2023. On the planning abilities of large language models - a critical investigation. In Proceedings of the Advances in Neural Information Processing Systems. 75993\u201376005."},{"key":"e_1_3_2_54_2","first-page":"5998","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Proceedings of the Advances in Neural Information Processing Systems. 5998\u20136008."},{"key":"e_1_3_2_55_2","unstructured":"Jian Wang Dongding Lin and Wenjie Li. 2022. Follow Me: Conversation planning for target-driven recommendation dialogue systems. arXiv:2208.03516. Retrieved from https:\/\/arxiv.org\/abs\/2208.03516"},{"key":"e_1_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3242071"},{"key":"e_1_3_2_57_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.362"},{"key":"e_1_3_2_58_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6453"},{"key":"e_1_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210061"},{"key":"e_1_3_2_60_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60450-9_8"},{"key":"e_1_3_2_61_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"e_1_3_2_62_2","volume-title":"Proceedings of the 7th International Conference on Learning Representations","author":"Wu Chien-sheng","year":"2019","unstructured":"Chien-sheng Wu, Richard Socher, and Caiming Xiong. 2019. Global-to-local memory pointer networks for task-oriented dialogue. In Proceedings of the 7th International Conference on Learning Representations."},{"key":"e_1_3_2_63_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1369"},{"key":"e_1_3_2_64_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.463"},{"key":"e_1_3_2_65_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6474"},{"key":"e_1_3_2_66_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.166"},{"key":"e_1_3_2_67_2","doi-asserted-by":"publisher","DOI":"10.1145\/3437963.3441791"},{"key":"e_1_3_2_68_2","first-page":"5591","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Yarats Denis","year":"2018","unstructured":"Denis Yarats and Mike Lewis. 2018. Hierarchical text generation and planning for strategic dialogue. In Proceedings of the International Conference on Machine Learning. 5591\u20135599."},{"key":"e_1_3_2_69_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.94"},{"key":"e_1_3_2_70_2","doi-asserted-by":"crossref","unstructured":"Tong Zhang Yong Liu Peixiang Zhong Chen Zhang Hao Wang and Chunyan Miao. 2021. KECRS: Towards knowledge-enriched conversational recommendation system. arXiv:2105.08261. Retrieved from https:\/\/arxiv.org\/abs\/2105.08261","DOI":"10.18653\/v1\/2022.nlp4convai-1.17"},{"key":"e_1_3_2_71_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-demos.30"},{"key":"e_1_3_2_72_2","unstructured":"Chujie Zheng and Minlie Huang. 2021. Exploring prompt-based few-shot learning for grounded dialog generation. arXiv:2109.06513. Retrieved from https:\/\/arxiv.org\/abs\/2109.06513"},{"key":"e_1_3_2_73_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i16.17712"},{"key":"e_1_3_2_74_2","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403143"},{"key":"e_1_3_2_75_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.365"},{"key":"e_1_3_2_76_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Zhou Yiheng","year":"2020","unstructured":"Yiheng Zhou, Yulia Tsvetkov, Alan W. Black, and Zhou Yu. 2020. Augmenting non-collaborative dialog systems with explicit semantic and strategic dialog history. In Proceedings of the International Conference on Learning Representations."}],"container-title":["ACM Transactions on Information Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3652598","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3652598","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:03:30Z","timestamp":1750291410000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3652598"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,27]]},"references-count":75,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2024,9,30]]}},"alternative-id":["10.1145\/3652598"],"URL":"https:\/\/doi.org\/10.1145\/3652598","relation":{},"ISSN":["1046-8188","1558-2868"],"issn-type":[{"value":"1046-8188","type":"print"},{"value":"1558-2868","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4,27]]},"assertion":[{"value":"2022-09-15","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-03-06","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-04-27","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}