{"type":"ScholarlyArticle","title":"TITAN : Task-oriented Dialogues with Mixed-Initiative Interactions","authors":[{"name":"Sitong Yan","slug":"sitong-yan","given":"Sitong","family":"Yan","affiliation":"School of Computer Science and Technology Xidian University , Xi'an , China"},{"name":"Shengli Song","slug":"shengli-song","given":"Shengli","family":"Song","affiliation":"School of Computer Science and Technology Xidian University , Xi'an , China"},{"name":"Jingyang Li","slug":"jingyang-li","given":"Jingyang","family":"Li","affiliation":"School of Computer Science and Technology Xidian University , Xi'an , China"},{"name":"Shiqi Meng","slug":"shiqi-meng","given":"Shiqi","family":"Meng","affiliation":"School of Computer Science and Technology Xidian University , Xi'an , China"},{"name":"Guangneng Hu","slug":"guangneng-hu","given":"Guangneng","family":"Hu","affiliation":"School of Computer Science and Technology Xidian University , Xi'an , China"}],"abstract":"In multi-domain task-oriented dialogue systems, users proactively propose a series of domain-specific requests that can often be under-or over-specified, sometimes with ambiguous and cross-domain demands. System-sided initiative would be necessary to identify certain situations and appropriately interact with users to resolve them. However, most existing task-oriented dialogue systems fail to consider such mixed-initiative interaction strategies, performing low efficiency and poor collaboration ability in human-computer conversation. In this paper, we construct a multi-domain task-oriented dialogue dataset with mixed-initiative strategies named TITAN from the large-scale dialogue corpus MultiWOZ 2.1. It contains a total of 1,800 human-human conversations where the system can either ask clarification questions actively or provides relevant information to address failure situations and implicit user requests. We report the results of several baseline models on system response generation and dialogue act prediction to assess the performance of SOTA methods on TITAN. These models can capture mixed-initiative dialogue acts, while remaining the deficiency to actively generate implicit requests and accurately provide alternative information, suggesting ample room for improvement in future studies.","doi":"10.24963/ijcai.2023/583","url":"https://ijcai.org/proceedings/2023/583","pdf":"https://ijcai.org/proceedings/2023/0583.pdf","markdown":"https://ijcai.org/proceedings/2023/583.md","bibtex":"https://ijcai.org/proceedings/2023/bibtex/583","volume":{"slug":"2023","title":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2023","url":"https://ijcai.org/proceedings/2023/","year":2023,"location":"Macao, SAR","dates":"19-25 August 2023","editors":"Edith Elkind","isbn":"978-1-956792-03-4","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2023"},"section":"Natural Language Processing","track":"Main Track","number":583,"pages":{"first":5251,"last":5259},"keywords":["Natural Language Processing: NLP: Language generation","Natural Language Processing: NLP: Resources and evaluation","Natural Language Processing: NLP: Dialogue and interactive systems"],"videos":[],"references":[{"position":1,"raw":"[Aliannejadi et al., 2019] Mohammad Aliannejadi, Hamed Zamani, Fabio A. Crestani, and W. Bruce Croft. Asking clarifying questions in open-domain information-seeking conversations. Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Infor- mation Retrieval, 2019.","title":"Asking clarifying questions in open-domain information-seeking conversations","authors":"Mohammad Aliannejadi, Hamed Zamani, Fabio A Crestani, W Bruce Croft","year":"2019","venue":"Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Balaraman and Magnini, 2020a] Vevake Balaraman and Bernardo Magnini. Investigating proactivity in task- oriented dialogues. In CLiC-it, 2020.","title":"Investigating proactivity in taskoriented dialogues","authors":"Magnini Balaraman, Vevake Balaraman, Bernardo Magnini","year":"2020","venue":"CLiC-it","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Balaraman and Magnini, 2020b] Vevake Balaraman and Bernardo Magnini. Proactive systems and influenceable users: Simulating proactivity in task-oriented dialogues. In Proc. 24th Workshop Semantics Pragmatics Dialogue-Full Papers, Virually at Brandeis, Waltham, New Jersey, July (SEMDIAL), pages 1-12, 2020.","title":"Proactive systems and influenceable users: Simulating proactivity in task-oriented dialogues","authors":"Magnini Balaraman, Vevake Balaraman, Bernardo Magnini","year":"2020","venue":"Proc. 24th Workshop Semantics Pragmatics Dialogue-Full Papers","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Balaraman et al., 2020] Vevake Balaraman, Bernardo Magnini, Fondazione Bruno Kessler, and Trento-Italy Povo. Investigating proactivity in task-oriented dialogues. Computational Linguistics CLiC-it 2020, page 23, 2020.","title":"Investigating proactivity in task-oriented dialogues","authors":"Balaraman","year":"2020","venue":"Computational Linguistics CLiC","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Budzianowski et al., 2018] Paweł Budzianowski, Tsung- Hsien Wen, Bo-Hsiang Tseng, Iñigo Casanueva, Stefan Ultes, Osman Ramadan, and Milica Gašić. MultiWOZ - a large-scale multi-domain Wizard-of-Oz dataset for task- oriented dialogue modelling. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 5016-5026, Brussels, Belgium, October- November 2018. Association for Computational Linguis- tics.","title":"MultiWOZa large-scale multi-domain Wizard-of-Oz dataset for taskoriented dialogue modelling","authors":"Paweł Budzianowski, Tsung-Hsien Wen, Bo-Hsiang Tseng, Iñigo Casanueva, Stefan Ultes, Milica Osman Ramadan, Gašić","year":"2018","venue":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Chen et al., 2019] Wenhu Chen, Jianshu Chen, Pengda Qin, Xifeng Yan, and William Yang Wang. Semantically con- ditioned dialog response generation via hierarchical disen- tangled self-attention. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 3696-3709, Florence, Italy, July 2019. Association for Computational Linguistics.","title":"Semantically conditioned dialog response generation via hierarchical disentangled self-attention","authors":"Chen","year":"2019","venue":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Deng et al., 2022] Yang Deng, Wenqiang Lei, Wenxuan Zhang, Wai Lam, and Tat-Seng Chua. Pacific: Toward- s proactive conversational question answering over tab- ular and textual data in finance. arXiv preprint arX- iv:2210.08817, 2022.","title":"Pacific: Towards proactive conversational question answering over tab-ular and textual data in finance","authors":"Yang Deng, Wenqiang Lei, Wenxuan Zhang, Wai Lam, Tat-Seng Chua","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Feng et al., 2020] Song Feng, Hui Wan, Chulaka Gu- nasekara, Siva Sankalp Patel, Sachindra Joshi, and Luis A Lastras. doc2dial: A goal-oriented document-grounded dialogue dataset. arXiv preprint arXiv:2011.06623, 2020.","title":"doc2dial: A goal-oriented document-grounded dialogue dataset","authors":"Song Feng, Hui Wan, Chulaka Gunasekara, Sankalp Siva, Sachindra Patel, Luis A Joshi, Lastras","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Feng et al., 2021] Song Feng, Siva Sankalp Patel, Hui Wan, and Sachindra Joshi. Multidoc2dial: Modeling dialogues grounded in multiple documents. In Conference on Empiri- cal Methods in Natural Language Processing, 2021.","title":"Multidoc2dial: Modeling dialogues grounded in multiple documents","authors":"Song Feng, Sankalp Siva, Hui Patel, Sachindra Wan, Joshi","year":"2021","venue":"Conference on Empirical Methods in Natural Language Processing","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Guo et al., 2021] M. Guo, Mingda Zhang, Siva Reddy, and Malihe Alikhani. Abg-coqa: Clarifying ambiguity in con- versational question answering. In Conference on Automat- ed Knowledge Base Construction, 2021.","title":"Abg-coqa: Clarifying ambiguity in conversational question answering","authors":"M Guo, Mingda Zhang, Siva Reddy, Malihe Alikhani","year":"2021","venue":"Conference on Automated Knowledge Base Construction","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[He et al., 2022] Wanwei He, Yinpei Dai, Yinhe Zheng, Yuchuan Wu, Zheng Cao, Dermot Liu, Peng Jiang, Min Yang, Fei Huang, Luo Si, et al. Galaxy: A generative pre- trained model for task-oriented dialog with semi-supervised learning and explicit policy injection. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 36, pages 10749-10757, 2022.","title":"Galaxy: A generative pretrained model for task-oriented dialog with semi-supervised learning and explicit policy injection","authors":"He","year":"2022","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Kraus et al., 2022a] Matthias Kraus, Nicolas Wagner, and Wolfgang Minker. ProDial -an annotated proactive dia- logue act corpus for conversational assistants using crowd- sourcing. In Proceedings of the Thirteenth Language Re- sources and Evaluation Conference, pages 3164-3173, Marseille, France, June 2022. European Language Re- sources Association.","title":"ProDial -an annotated proactive dialogue act corpus for conversational assistants using crowdsourcing","authors":"Kraus","year":"2022","venue":"Proceedings of the Thirteenth Language Resources and Evaluation Conference","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Kraus et al., 2022b] Matthias Kraus, Nicolas Wagner, and Wolfgang Minker. Prodial-an annotated proactive dialogue act corpus for conversational assistants using crowdsourc- ing. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 3164-3173, 2022.","title":"Prodial-an annotated proactive dialogue act corpus for conversational assistants using crowdsourcing","authors":"Kraus","year":"2022","venue":"Proceedings of the Thirteenth Language Resources and Evaluation Conference","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Le et al., 2020] Hung Le, Doyen Sahoo, Chenghao Liu, Nan- cy Chen, and Steven C.H. Hoi. UniConv: A unified conver- sational neural architecture for multi-domain task-oriented dialogues. In Proceedings of the 2020 Conference on Em- pirical Methods in Natural Language Processing (EMNLP), pages 1860-1877, Online, November 2020. Association for Computational Linguistics.","title":"UniConv: A unified conversational neural architecture for multi-domain task-oriented dialogues","authors":"Hung Le, Doyen Sahoo, Chenghao Liu, Nancy Chen, Steven C H Hoi","year":"2020","venue":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Lee, 2021] Yohan Lee. Improving end-to-end task-oriented dialog system with a simple auxiliary task. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 1296-1303, 2021.","title":"Improving end-to-end task-oriented dialog system with a simple auxiliary task","authors":"Yohan Lee","year":"2021","venue":"Findings of the Association for Computational Linguistics: EMNLP 2021","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Mass et al., 2021] Yosi Mass, Doron Cohen, Asaf Yehudai, and David Konopnicki. Conversational search with mixed- initiative-asking good clarification questions backed-up by passage retrieval. arXiv preprint arXiv:2112.07308, 2021.","title":"Conversational search with mixedinitiative-asking good clarification questions backed-up by passage retrieval","authors":"Yosi Mass, Doron Cohen, Asaf Yehudai, David Konopnicki","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Raux et al., 2005] Antoine Raux, Brian Langner, Dan Bohus, Alan W Black, and Maxine Eskenazi. Let's go public! taking a spoken dialog system to the real world. In in Proc. of Interspeech 2005. Citeseer, 2005.","title":"Let's go public! taking a spoken dialog system to the real world","authors":"Antoine Raux, Brian Langner, Dan Bohus, Alan W Black, Maxine Eskenazi","year":"2005","venue":"Proc. of Interspeech 2005","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Saeidi et al., 2018] Marzieh Saeidi, Max Bartolo, Patrick Lewis, Sameer Singh, Tim Rocktäschel, Mike Sheldon, Guillaume Bouchard, and Sebastian Riedel. Interpretation of natural language rules in conversational machine reading. ArXiv, abs/1809.01494, 2018.","title":"Interpretation of natural language rules in conversational machine reading","authors":"Marzieh Saeidi, Max Bartolo, Patrick Lewis, Sameer Singh, Tim Rocktäschel, Mike Sheldon, Guillaume Bouchard, Sebastian Riedel","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Seneff and Polifroni, 2000] Stephanie Seneff and Joseph Po- lifroni. Dialogue management in the mercury flight reser- vation system. In ANLP-NAACL 2000 Workshop: Conver- sational Systems, 2000.","title":"Dialogue management in the mercury flight reservation system","authors":"Stephanie Seneff, Joseph Polifroni","year":"2000","venue":"ANLP-NAACL 2000 Workshop: Conversational Systems","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Shi et al., 2022] Zhengxiang Shi, Yue Feng, and Aldo Lipani. Learning to execute actions or ask clarification questions. In Findings of the Association for Computational Linguistics: NAACL 2022, pages 2060-2070, 2022.","title":"Learning to execute actions or ask clarification questions","authors":"Shi","year":"2022","venue":"Findings of the Association for Computational Linguistics: NAACL 2022","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Sun et al., 2022] Haipeng Sun, Junwei Bao, Youzheng Wu, and Xiaodong He. Bort: Back and denoising reconstruc- tion for end-to-end task-oriented dialog. arXiv preprint arXiv:2205.02471, 2022.","title":"Bort: Back and denoising reconstruction for end-to-end task-oriented dialog","authors":"Haipeng Sun, Junwei Bao, Youzheng Wu, Xiaodong He","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Vakulenko et al., 2021] Svitlana Vakulenko, Evangelos Kanoulas, and Maarten De Rijke. A large-scale analysis of mixed initiative in information-seeking dialogues for conversational search. ACM Transactions on Information Systems (TOIS), 39(4):1-32, 2021.","title":"A large-scale analysis of mixed initiative in information-seeking dialogues for conversational search","authors":"Svitlana Vakulenko, Evangelos Kanoulas, Maarten De, Rijke","year":"2021","venue":"ACM Transactions on Information Systems (TOIS)","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Wadhwa and Zamani, 2021] Somin Wadhwa and Hamed Za- mani. Towards system-initiative conversational information seeking. In DESIRES, 2021.","title":"Towards system-initiative conversational information seeking","authors":"Wadhwa, Zamani ;, Hamed Zamani","year":"2021","venue":"Somin Wadhwa","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Walker and Whittaker, 1990] Marilyn Walker and Steve Whittaker. Mixed initiative in dialogue: An investigation into discourse segmentation. In 28th Annual Meeting of the Association for Computational Linguistics, pages 70-78, Pittsburgh, Pennsylvania, USA, June 1990. Association for Computational Linguistics.","title":"Mixed initiative in dialogue: An investigation into discourse segmentation","authors":"Whittaker ; Walker, Marilyn Walker, Steve Whittaker","year":"1990","venue":"28th Annual Meeting of the Association for Computational Linguistics","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Walker and Whittaker, 1995] Marilyn Walker and Steve Whittaker. Mixed initiative in dialogue: An investigation in- to discourse segmentation. arXiv preprint cmp-lg/9504007, 1995.","title":"Mixed initiative in dialogue: An investigation into discourse segmentation","authors":"Whittaker ; Walker, Marilyn Walker, Steve Whittaker","year":"1995","venue":null,"doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Wang et al., 2020] Kai Wang, Junfeng Tian, Rui Wang, Xi- aojun Quan, and Jianxing Yu. Multi-domain dialogue acts and response co-generation. In Proceedings of the 58th Annual Meeting of the Association for Computational Lin- guistics, pages 7125-7134, Online, July 2020. Association for Computational Linguistics.","title":"Multi-domain dialogue acts and response co-generation","authors":"Kai Wang, Junfeng Tian, Rui Wang, Xiaojun Quan, Jianxing Yu","year":"2020","venue":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Wen et al., 2015] Tsung-Hsien Wen, Milica Gašić, Nikola Mrkšić, Pei-Hao Su, David Vandyke, and Steve Young. Semantically conditioned LSTM-based natural language generation for spoken dialogue systems. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pages 1711-1721, Lisbon, Portugal, September 2015. Association for Computational Linguis- tics.","title":"Semantically conditioned LSTM-based natural language generation for spoken dialogue systems","authors":"Tsung-Hsien Wen, Milica Gašić, Nikola Mrkšić, Pei-Hao Su, David Vandyke, Steve Young","year":"2015","venue":"Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Wu et al., 2019a] Wenquan Wu, Zhen Guo, Xiangyang Zhou, Hua Wu, Xiyuan Zhang, Rongzhong Lian, and Haifeng Wang. Proactive human-machine conversation with explicit conversation goal. In Proceedings of the 57th Annual Meeting of the Association for Computational Lin- guistics, pages 3794-3804, Florence, Italy, July 2019. As- sociation for Computational Linguistics.","title":"Proactive human-machine conversation with explicit conversation goal","authors":"Wu","year":"2019","venue":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Wu et al., 2019b] Wenquan Wu, Zhen Guo, Xiangyang Zhou, Hua Wu, Xiyuan Zhang, Rongzhong Lian, and Haifeng Wang. Proactive human-machine conversation with explicit conversation goals. arXiv preprint arX- iv:1906.05572, 2019.","title":"Proactive human-machine conversation with explicit conversation goals","authors":"Wu","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Wu et al., 2022] Zeqiu Wu, Ryu Parish, Hao Cheng, Sewon Min, Prithviraj Ammanabrolu, Mari Ostendorf, and Han- naneh Hajishirzi. Inscit: Information-seeking conversa- tions with mixed-initiative interactions. arXiv preprint arXiv:2207.00746, 2022.","title":"Inscit: Information-seeking conversations with mixed-initiative interactions","authors":"Zeqiu Wu, Ryu Parish, Hao Cheng, Sewon Min, Prithviraj Ammanabrolu, Mari Ostendorf, Hannaneh Hajishirzi","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Yang and Heeman, 2007] Fan Yang and Peter A Heeman. Exploring initiative strategies using computer simulation. In Eighth Annual Conference of the International Speech Communication Association, 2007.","title":"Exploring initiative strategies using computer simulation","authors":"Fan Yang, Peter A Heeman","year":"2007","venue":"Eighth Annual Conference of the International Speech Communication Association","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Yang et al., 2004] Fan Yang, Peter A Heeman, and Kristy Hollingshead. Towards understanding mixed-initiative in task-oriented dialogues. In Eighth International Conference on Spoken Language Processing, 2004.","title":"Towards understanding mixed-initiative in task-oriented dialogues","authors":"Fan Yang, Peter A Heeman, Kristy Hollingshead","year":"2004","venue":"Eighth International Conference on Spoken Language Processing","doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Yang et al., 2021] Yunyi Yang, Yunhao Li, and Xiaojun Quan. Ubar: Towards fully end-to-end task-oriented dialog system with gpt-2. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, pages 14230-14238, 2021.","title":"Ubar: Towards fully end-to-end task-oriented dialog system with gpt-2","authors":"Yang","year":"2021","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":34,"raw":"[Young et al., 2022] Tom Young, Frank Xing, Vlad Pande- lea, Jinjie Ni, and Erik Cambria. Fusing task-oriented and open-domain dialogues in conversational agents. In Pro- ceedings of the AAAI Conference on Artificial Intelligence, volume 36, pages 11622-11629, 2022.","title":"Fusing task-oriented and open-domain dialogues in conversational agents","authors":"Tom Young, Frank Xing, Vlad Pandelea, Jinjie Ni, Erik Cambria","year":"2022","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":35,"raw":"[Zhang et al., 2020] Yichi Zhang, Zhijian Ou, Min Hu, and Junlan Feng. A probabilistic end-to-end task-oriented dia- log model with latent belief states towards semi-supervised learning. In Proceedings of the 2020 Conference on Empir- ical Methods in Natural Language Processing (EMNLP), pages 9207-9219, Online, November 2020. Association for Computational Linguistics.","title":"A probabilistic end-to-end task-oriented dialog model with latent belief states towards semi-supervised learning","authors":"Zhang","year":"2020","venue":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)","doi":null,"url":null,"internal_url":null},{"position":36,"raw":"[Zhao et al., 2023] Meng Zhao, Lifang Wang, Zejun Jiang, Ronghan Li, Xinyu Lu, and Zhongtian Hu. Multi-task learning with graph attention networks for multi-domain task-oriented dialogue systems. Knowledge-Based Systems, 259:110069, 2023.","title":"Multi-task learning with graph attention networks for multi-domain task-oriented dialogue systems","authors":"Meng Zhao, Lifang Wang, Zejun Jiang, Ronghan Li, Xinyu Lu, Zhongtian Hu","year":"2023","venue":"Knowledge-Based Systems","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}