Translated Abstract
In dialogue services, a dialogue handover, where one operator transfers the conversation to another operator to respond to the user’s requests, occurs frequently. For a smooth handover, it is essential for the operator taking over to have a proper understanding of the dialogue context. However, it is unclear what information is useful for handover. In this study, we explored what information would be useful for operators to seamlessly continue dialogues through a dialogue handover experiment. Specifically, operators were made to take notes during the dialogue with the user, and these notes were used to hand over the dialogue to another operator repeatedly. By analyzing the content of the notes that converged through this process, we investigated the useful information for dialogue handover. As a result, it was found that sequence organizations are effective for chit-chat, while key-value pairs are more suitable for task-oriented dialogues. This finding is considered useful for constructing interfaces that facilitate dialogue handover.
References
- [1] Yamashita, S. and Higashinaka, R.: Data Collection for Empirically Determining the Necessary Information for Smooth Handover in Dialogue, Proceedings of the Thirteenth Language Resources and Evaluation Conference, pp. 4060–4068 (2022).
- [2] Forman, G., Kirshenbaum, E. and Suermondt, J.: Pragmatic Text Mining: Minimizing Human Effort to Quantify Many Issues in Call Logs, Proceedings of the 12th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 852–861 (2006).
- [3] Nasukawa, T.: Text Mining Application for Call Centers, Journal of the Japanese Society for Artificial Intelligence, Vol. 16, No. 2, pp. 219–225 (2001). (in Japanese).
- [4] Tamura, A., Ishikawa, K., Saikou, M. and Tsuchida, M.: Extractive Summarization Method for Contact Center Dialogues based on Call Logs, Proceedings of 5th International Joint Conference on Natural Language Processing, pp. 500–508 (2011).
- [5] Arimoto, T., Higashinaka, R., Tanaka, K., Kawanishi, T., Sugiyama, H., Sawada, H. and Ishiguro, H.: Collection and Analysis of Dialogues Provided by Two Speakers Acting as One, Proceedings of the 21th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pp. 323–328 (2020).
- [6] Lasecki , W. S., Wesley, R., Nichols, J., Kulkarni, A., Allen , J. F. and Bigham , J. P.: Chorus: A Crowd-Powered Conversational Assistant, Proceedings of the 26th Annual ACM Symposium on User Interface Software and Technology, pp. 151–162 (2013).
- [7] Huang, T.-H., Chang , J. C. and Bigham , J. P.: Evorus: A Crowd-Powered Conversational Assistant Built to Automate Itself Over Time, Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems, pp. 1–13 (2018).
- [8] Kawahara, T., Muramatsu, N., Yamamoto, K., Lala, D. and Inoue, K.: Semi-Autonomous Avatar Enabling Unconstrained Parallel Conversations–Seamless Hybrid of WOZ and Autonomous Dialogue Systems–, Advanced Robotics, pp. 1–7 (2021).
- [9] Kawai, H., Muraki, Y., Yamamoto, K., Lala, D., Inoue, K. and Kawahara, T.: Simultaneous Job Interview System Using Multiple Semi-autonomous Agents, Proceedings of the 23rd Annual Meeting of the Special Interest Group on Discourse and Dialogue, pp. 107–110 (2022).
- [10] Kawai, H., Lala, D., Inoue, K., Ochi, K. and Kawahara, T.: Evaluation of a Semi-Autonomous Attentive Listening System with Takeover Prompting, arXiv preprint arXiv:2402.14863 (2024).
- [11] Kawasaki, K. and Ogawa, K.: Development of Simultaneous Summarizing Technology of Multiple Sites Context for Multiple Agent Tele-Operation System, Proceedings of the Annual Conference of JSAI, Vol. JSAI2022, p. 2F1GS904 (2022). (in Japanese).
- [12] Yamashita, S., Mochizuki, S., Kawasaki, K., Kubota, T., Ogawa, K., Baba, J. and Higashinaka, R.: Investigating the Effects of Dialogue Summarization on Intervention in Human-System Collaborative Dialogue, Proceedings of the 11th International Conference on Human-Agent Interaction, pp. 316–324 (2023).
- [13] Schegloff , E. A.: Sequence Organization in Interaction: A Primer in Conversation Analysis, Vol. 1, Cambridge University Press (2007).
- [14] Schegloff , E. A. and Sacks, H.: Opening up Closings, Semiotica, Vol. 8, No. 4, pp. 289–327 (1973).
- [15] Tsui , A. B. M.: Beyond the Adjacency Pair, Language in Society, Vol. 18, No. 4, pp. 545–564 (1989).
- [16] Enomoto, M., Den, Y. and Matsusaka, Y.: Annotation of Dialog Acts and Addressees in Three-Party Conversations and its Preliminary Analysis, JSAI Technical Report, SIG-SLUD, Vol. 45, pp. 7–12 (2005). (in Japanese).
- [17] Williams, J. D. and Young, S.: Partially Observable Markov Decision Processes for Spoken Dialog Systems, Computer Speech & Language, Vol. 21, No. 2, pp. 393–422 (2007).
- [18] Williams , J. D., Henderson, M., Raux, A., Thomson, B., Black, A. and Ramachandran, D.: The Dialog State Tracking Challenge Series, AI Magazine, Vol. 35, No. 4, pp. 121–124 (2014).
- [19] Kudo, T., Yamamoto, K. and Matsumoto, Y.: Applying Conditional Random Fields to Japanese Morphological Analysis, Proceedings of the 2004 Conference on Empirical Methods in Natural Language Processing, pp. 230–237 (2004).
