{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T03:38:01Z","timestamp":1776310681861,"version":"3.50.1"},"reference-count":48,"publisher":"Association for Computing Machinery (ACM)","issue":"1","license":[{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Science and Technology Innovation 2030 Major Project of China","award":["2020AAA0108605"],"award-info":[{"award-number":["2020AAA0108605"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62076081, 61772153, and 61936010"],"award-info":[{"award-number":["62076081, 61772153, and 61936010"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Inf. Syst."],"published-print":{"date-parts":[[2023,1,31]]},"abstract":"<jats:p>Recently, research on open domain dialogue systems have attracted extensive interests of academic and industrial researchers. The goal of an open domain dialogue system is to imitate humans in conversations. Previous works on single turn conversation generation have greatly promoted the research of open domain dialogue systems. However, understanding multiple single turn conversations is not equal to the understanding of multi turn dialogue due to the coherent and context dependent properties of human dialogue. Therefore, in open domain multi turn dialogue generation, it is essential to modeling the contextual semantics of the dialogue history rather than only according to the last utterance. Previous research had verified the effectiveness of the hierarchical recurrent encoder-decoder framework on open domain multi turn dialogue generation. However, using an RNN-based model to hierarchically encoding the utterances to obtain the representation of dialogue history still face the problem of a vanishing gradient. To address this issue, in this article, we proposed a static and dynamic attention-based approach to model the dialogue history and then generate open domain multi turn dialogue responses. Experimental results on the Ubuntu and Opensubtitles datasets verify the effectiveness of the proposed static and dynamic attention-based approach on automatic and human evaluation metrics in various experimental settings. Meanwhile, we also empirically verify the performance of combining the static and dynamic attentions on open domain multi turn dialogue generation.<\/jats:p>","DOI":"10.1145\/3522763","type":"journal-article","created":{"date-parts":[[2022,6,30]],"date-time":"2022-06-30T10:18:21Z","timestamp":1656584301000},"page":"1-30","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":13,"title":["A Static and Dynamic Attention Framework for Multi Turn Dialogue Generation"],"prefix":"10.1145","volume":"41","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5981-4752","authenticated-orcid":false,"given":"Weinan","family":"Zhang","sequence":"first","affiliation":[{"name":"Research Center for Social Computing and Information Retrieval, Harbin Institute of Technology, Harbin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4872-5145","authenticated-orcid":false,"given":"Yiming","family":"Cui","sequence":"additional","affiliation":[{"name":"Research Center for Social Computing and Information Retrieval, Harbin Institute of Technology; State Key Laboratory of Cognitive Intelligence, iFLYTEK Research, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2452-375X","authenticated-orcid":false,"given":"Kaiyan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Research Center for Social Computing and Information Retrieval, Harbin Institute of Technology, Harbin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0922-8912","authenticated-orcid":false,"given":"Yifa","family":"Wang","sequence":"additional","affiliation":[{"name":"Research Center for Social Computing and Information Retrieval, Harbin Institute of Technology, Harbin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3395-222X","authenticated-orcid":false,"given":"Qingfu","family":"Zhu","sequence":"additional","affiliation":[{"name":"Research Center for Social Computing and Information Retrieval, Harbin Institute of Technology, Harbin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3004-9641","authenticated-orcid":false,"given":"Lingzhi","family":"Li","sequence":"additional","affiliation":[{"name":"Research Center for Social Computing and Information Retrieval, Harbin Institute of Technology, Harbin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9091-7757","authenticated-orcid":false,"given":"Ting","family":"Liu","sequence":"additional","affiliation":[{"name":"Research Center for Social Computing and Information Retrieval, Harbin Institute of Technology, Harbin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,1,9]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"crossref","first-page":"78","DOI":"10.18653\/v1\/S17-1008","volume-title":"Proceedings of the 6th Joint Conference on Lexical and Computational Semantics (*SEM 2017)","author":"Asghar Nabiha","year":"2017","unstructured":"Nabiha Asghar, Pascal Poupart, Xin Jiang, and Hang Li. 2017. Deep active learning for dialogue generation. In Proceedings of the 6th Joint Conference on Lexical and Computational Semantics (*SEM 2017). Association for Computational Linguistics, Vancouver, Canada, 78\u201383. http:\/\/www.aclweb.org\/anthology\/S17-1008."},{"key":"e_1_3_2_3_2","article-title":"Neural machine translation by jointly learning to align and translate","volume":"1409","author":"Bahdanau Dzmitry","year":"2014","unstructured":"Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. 2014. Neural machine translation by jointly learning to align and translate. CoRR abs\/1409.0473 (2014).","journal-title":"CoRR"},{"key":"e_1_3_2_4_2","first-page":"37","volume-title":"ACL","author":"Banchs Rafael E.","year":"2012","unstructured":"Rafael E. Banchs and Haizhou Li. 2012. IRIS: A chat-oriented dialogue system based on the vector space model. In ACL. 37\u201342."},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401461"},{"key":"e_1_3_2_6_2","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"Chung Junyoung","year":"2014","unstructured":"Junyoung Chung, Caglar Gulcehre, KyungHyun Cho, and Yoshua Bengio. 2014. Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555 (2014).","journal-title":"arXiv preprint arXiv:1412.3555"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403211"},{"issue":"3","key":"e_1_3_2_8_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3383123","article-title":"Challenges in building intelligent open-domain dialog systems","volume":"38","author":"Huang Minlie","year":"2020","unstructured":"Minlie Huang, Xiaoyan Zhu, and Jianfeng Gao. 2020. Challenges in building intelligent open-domain dialog systems. ACM Transactions on Information Systems (TOIS) 38, 3 (2020), 1\u201332.","journal-title":"ACM Transactions on Information Systems (TOIS)"},{"key":"e_1_3_2_9_2","article-title":"When to talk: Chatbot controls the timing of talking during multi-turn open-domain dialogue generation","author":"Lan Tian","year":"2019","unstructured":"Tian Lan, Xianling Mao, Heyan Huang, and Wei Wei. 2019. When to talk: Chatbot controls the timing of talking during multi-turn open-domain dialogue generation. arXiv preprint arXiv:1912.09879 (2019).","journal-title":"arXiv preprint arXiv:1912.09879"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1014"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1094"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1127"},{"key":"e_1_3_2_13_2","first-page":"1186","volume-title":"2019 IEEE International Conference on Data Mining (ICDM)","author":"Li Yongrui","year":"2019","unstructured":"Yongrui Li, Jun Yu, and Zengfu Wang. 2019. Dense semantic matching network for multi-turn conversation. In 2019 IEEE International Conference on Data Mining (ICDM). IEEE, 1186\u20131191."},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3379996"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W15-4640"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401255"},{"key":"e_1_3_2_17_2","first-page":"311","volume-title":"ACL","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 ACL. 311\u2013318."},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/3394592"},{"key":"e_1_3_2_19_2","first-page":"172","volume-title":"NAACL","author":"Ritter Alan","year":"2010","unstructured":"Alan Ritter, Colin Cherry, and Bill Dolan. 2010. Unsupervised modeling of twitter conversations. In NAACL. 172\u2013180."},{"key":"e_1_3_2_20_2","first-page":"583","volume-title":"EMNLP","author":"Ritter Alan","year":"2011","unstructured":"Alan Ritter, Colin Cherry, and William B. Dolan. 2011. Data-driven response generation in social media. In EMNLP. 583\u2013593."},{"key":"e_1_3_2_21_2","doi-asserted-by":"crossref","unstructured":"Iulian Serban Tim Klinger Gerald Tesauro Kartik Talamadupula Bowen Zhou Yoshua Bengio and Aaron Courville. 2017. Multiresolution Recurrent Neural Networks: An Application to Dialogue Response Generation. (2017).","DOI":"10.1609\/aaai.v31i1.10984"},{"key":"e_1_3_2_22_2","doi-asserted-by":"crossref","unstructured":"Iulian Serban Alessandro Sordoni Yoshua Bengio Aaron Courville and Joelle Pineau. 2016. Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models. (2016).","DOI":"10.1609\/aaai.v30i1.9883"},{"key":"e_1_3_2_23_2","article-title":"Multiresolution recurrent neural networks: An application to dialogue response generation","author":"Serban Iulian Vlad","year":"2016","unstructured":"Iulian Vlad Serban, Tim Klinger, Gerald Tesauro, Kartik Talamadupula, Bowen Zhou, Yoshua Bengio, and Aaron Courville. 2016. Multiresolution recurrent neural networks: An application to dialogue response generation. arXiv preprint arXiv:1606.00776 (2016).","journal-title":"arXiv preprint arXiv:1606.00776"},{"key":"e_1_3_2_24_2","doi-asserted-by":"crossref","unstructured":"Iulian Vlad Serban Alessandro Sordoni Ryan Lowe Laurent Charlin Joelle Pineau Aaron C Courville and Yoshua Bengio. 2017. A hierarchical latent variable encoder-decoder model for generating dialogues. (2017) 3295\u20133301.","DOI":"10.1609\/aaai.v31i1.10983"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-1152"},{"key":"e_1_3_2_26_2","first-page":"2200","volume-title":"Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing","author":"Shao Yuanlong","year":"2017","unstructured":"Yuanlong Shao, Stephan Gouws, Denny Britz, Anna Goldie, Brian Strope, and Ray Kurzweil. 2017. Generating high-quality and informative conversation responses with sequence-to-sequence models. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, 2200\u20132209. http:\/\/www.aclweb.org\/anthology\/D17-1234"},{"key":"e_1_3_2_27_2","doi-asserted-by":"crossref","first-page":"5497","DOI":"10.18653\/v1\/P19-1549","volume-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","author":"Shen Lei","year":"2019","unstructured":"Lei Shen, Yang Feng, and Haolan Zhan. 2019. Modeling semantic relationship in multi-turn conversations with hierarchical latent variables. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. 5497\u20135502."},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-2080"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"e_1_3_2_30_2","first-page":"8976","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","volume":"34","author":"Sun Zewei","year":"2020","unstructured":"Zewei Sun, Shujian Huang, Hao-Ran Wei, Xin-yu Dai, and Jiajun Chen. 2020. Generating diverse translation by manipulating multi-head attention. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 34. 8976\u20138983."},{"key":"e_1_3_2_31_2","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","volume":"4","author":"Sutskever Ilya","year":"2014","unstructured":"Ilya Sutskever, Oriol Vinyals, Quoc V. Le, Ilya Sutskever, Oriol Vinyals, and Quoc V. Le. 2014. Sequence to sequence learning with neural networks. NIPS 4 (2014), 3104\u20133112.","journal-title":"NIPS"},{"key":"e_1_3_2_32_2","doi-asserted-by":"crossref","first-page":"231","DOI":"10.18653\/v1\/P17-2036","volume-title":"Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","author":"Tian Zhiliang","year":"2017","unstructured":"Zhiliang Tian, Rui Yan, Lili Mou, Yiping Song, Yansong Feng, and Dongyan Zhao. 2017. How to make context more useful? An empirical study on context-aware neural conversational models. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers). Association for Computational Linguistics, 231\u2013236. DOI:https:\/\/doi.org\/10.18653\/v1\/P17-2036"},{"key":"e_1_3_2_33_2","volume-title":"News from OPUS - A Collection of Multilingual Parallel Corpora with Tools and Interfaces","author":"Tiedemann J","year":"2009","unstructured":"J Tiedemann. 2009. News from OPUS - A Collection of Multilingual Parallel Corpora with Tools and Interfaces. 237\u2013248 pages."},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1093\/mind\/LIX.236.433"},{"key":"e_1_3_2_35_2","first-page":"5998","volume-title":"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 Advances in Neural Information Processing Systems. 5998\u20136008."},{"key":"e_1_3_2_36_2","article-title":"A neural conversational model","author":"Vinyals Oriol","year":"2015","unstructured":"Oriol Vinyals and Quoc Le. 2015. A neural conversational model. arXiv preprint arXiv:1506.05869 (2015).","journal-title":"arXiv preprint arXiv:1506.05869"},{"key":"e_1_3_2_37_2","article-title":"Hierarchical recurrent attention network for response generation","author":"Xing Chen","year":"2017","unstructured":"Chen Xing, Wei Wu, Yu Wu, Ming Zhou, Yalou Huang, and Wei-Ying Ma. 2017. Hierarchical recurrent attention network for response generation. arXiv preprint arXiv:1701.07149 (2017).","journal-title":"arXiv preprint arXiv:1701.07149"},{"key":"e_1_3_2_38_2","first-page":"2180","volume-title":"Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing","author":"Yao Lili","year":"2017","unstructured":"Lili Yao, Yaoyuan Zhang, Yansong Feng, Dongyan Zhao, and Rui Yan. 2017. Towards implicit content-introducing for generative short-text conversation systems. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, 2180\u20132189. http:\/\/www.aclweb.org\/anthology\/D17-1232."},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10804"},{"key":"e_1_3_2_40_2","doi-asserted-by":"crossref","first-page":"3721","DOI":"10.18653\/v1\/P19-1362","volume-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","author":"Zhang Hainan","year":"2019","unstructured":"Hainan Zhang, Yanyan Lan, Liang Pang, Jiafeng Guo, and Xueqi Cheng. 2019. ReCoSa: Detecting the relevant contexts with self-attention for multi-turn dialogue generation. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. 3721\u20133730."},{"key":"e_1_3_2_41_2","first-page":"2437","volume-title":"Proceedings of the 27th International Conference on Computational Linguistics","author":"Zhang Weinan","year":"2018","unstructured":"Weinan Zhang, Yiming Cui, Yifa Wang, Qingfu Zhu, Lingzhi Li, Lianqiang Zhou, and Ting Liu. 2018. Context-sensitive generation of open-domain conversational responses. In Proceedings of the 27th International Conference on Computational Linguistics. 2437\u20132447."},{"key":"e_1_3_2_42_2","volume-title":"Thirty-Second AAAI Conference on Artificial Intelligence","author":"Zhang Wei-Nan","year":"2018","unstructured":"Wei-Nan Zhang, Lingzhi Li, Dongyan Cao, and Ting Liu. 2018. Exploring implicit feedback for open domain conversation generation. In Thirty-Second AAAI Conference on Artificial Intelligence."},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11280-018-0598-6"},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1061"},{"key":"e_1_3_2_45_2","doi-asserted-by":"crossref","first-page":"1834","DOI":"10.18653\/v1\/D19-1192","volume-title":"Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)","author":"Zhou Kun","year":"2019","unstructured":"Kun Zhou, Kai Zhang, Yu Wu, Shujie Liu, and Jingsong Yu. 2019. Unsupervised context rewriting for open domain conversation. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 1834\u20131844."},{"key":"e_1_3_2_46_2","first-page":"3763","volume-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","author":"Zhu Qingfu","year":"2019","unstructured":"Qingfu Zhu, Lei Cui, Weinan Zhang, Furu Wei, and Ting Liu. 2019. Retrieval-enhanced adversarial training for neural response generation. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. 3763\u20133773."},{"issue":"2","key":"e_1_3_2_47_2","first-page":"1","article-title":"Order-sensitive keywords based response generation in open-domain conversational systems","volume":"19","author":"Zhu Qingfu","year":"2019","unstructured":"Qingfu Zhu, Weinan Zhang, Lei Cui, and Ting Liu. 2019. Order-sensitive keywords based response generation in open-domain conversational systems. ACM Transactions on Asian and Low-Resource Language Information Processing (TALLIP) 19, 2 (2019), 1\u201318.","journal-title":"ACM Transactions on Asian and Low-Resource Language Information Processing (TALLIP)"},{"key":"e_1_3_2_48_2","first-page":"3438","volume-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)","author":"Zhu Qingfu","year":"2020","unstructured":"Qingfu Zhu, Weinan Zhang, Ting Liu, and William Yang Wang. 2020. Counterfactual off-policy training for neural dialogue generation. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). 3438\u20133448."},{"key":"e_1_3_2_49_2","article-title":"Learning to start for sequence to sequence architecture","author":"Zhu Qingfu","year":"2016","unstructured":"Qingfu Zhu, Weinan Zhang, Lianqiang Zhou, and Ting Liu. 2016. Learning to start for sequence to sequence architecture. arXiv preprint arXiv:1608.05554 (2016).","journal-title":"arXiv preprint arXiv:1608.05554"}],"container-title":["ACM Transactions on Information Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3522763","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3522763","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:30:16Z","timestamp":1750188616000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3522763"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,9]]},"references-count":48,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2023,1,31]]}},"alternative-id":["10.1145\/3522763"],"URL":"https:\/\/doi.org\/10.1145\/3522763","relation":{},"ISSN":["1046-8188","1558-2868"],"issn-type":[{"value":"1046-8188","type":"print"},{"value":"1558-2868","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1,9]]},"assertion":[{"value":"2021-01-13","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-02-27","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-01-09","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}