Program

Conference Rooms 5a & 5b

• 13:00 - 13:15  Opening

• 13:15 - 14:00  Keynote 1: Koichiro Yoshino

• 14:00 - 14:20  Coffee Break + Presentation Setup

• 14:20 - 15:20  Position Talks (Oral) 1 : 10 presentations

• 15:20 - 15:45  Coffee Break + Roundtable Setup

• 15:45 - 16:15  Roundtable 1

• 16:15 - 16:45  Coffee Break + Presentation Setup

• 16:45 - 17:45  Position Talks (Oral) 2 : 10 presentations

• 18:00 - 19:00  Casual Dinner

Symposium Hall (Morning)

• 09:30 - 10:15  Keynote 2: Yoichi Matsuyama

• 10:15 - 10:30  Coffee Break + Presentation Setup

• 10:30 - 11:45  Position Talks (Oral) 3 : 12 presentations

• 11:45 - 13:30  Lunch break & Registration Desk Open

Conference Rooms 5a & 5b (Afternoon)

• 13:30 - 14:00  Roundtable 2

• 14:00 - 14:30  Coffee Break + Roundtable Setup

• 14:30 - 15:00  Roundtable 3

• 15:30 - 15:45  Wrap up

• 15:45 - 16:00  Photo Session

• 16:00 - 18:00  Social Activity

Position Talks 1 (Day1)

• • Conversational XAI and Explanation Dialogues (Nils Feldhus)

  • Enhancing Emotion Recognition in Spoken Dialogue Systems through Multimodal Integration and Personalization (Takumasa Kaneko)

  • Towards Personalisation of User Support Systems. (Tomoya Higuchi)

  • Social agents for positively influencing human psychological states (Muhammad Yeza Baihaqi)

  • Personalized Topic Transition for Dialogue System (Kai Yoshida)

  • Elucidation of psychotherapy and development of new treatment methods using AI (Shio Maeda)

  • Assessing Interactional Competence with Multimodal Dialog Systems (Mao Saeki)

  • Faithfulness of Natural Language Generation (Patricia Schmidtova)

  • Knowledge-Grounded Dialogue Systems for Generating Interesting and Engaging Responses (Hiroki Onozeki)

  • Towards a Dialogue System that Can Take Interlocutors' Values into Account (Yuki Zenimoto)

Position Talks 2 (Day1)

• • Multimodal Spoken Dialogue System with Biosignals (Shun Katada)

  • Timing Sensitive Turn-Taking in Spoken Dialogue Systems Based on User Satisfaction (Sadahiro Yoshikawa)

  • Towards Robust and Multilingual Task-Oriented Dialogue Systems (Atsumoto Ohashi)

  • Toward Faithful Dialogs: Evaluating and Improving the Faithfulness of Dialog Systems (Sicong Huang)

  • Cognitive model of listener response generation and its application to dialogue systems (Taiga Mori)

  • Topological Deep Learning for Term Extraction (Benjamin Matthias Ruppik)

  • Dialogue Management with Graph-structured Knowledge (Nicholas Thomas Walker)

  • Towards a co-creation dialogue system (Xulin Zhou)

  • Enhancing Decision-Making with AI Assistance (Yoshiki Tanaka)

  • Ontology Construction for Task-oriented Dialogue (Renato Vukovic)

Position Talks 3 (Day2)

• • Generalized Visual-Language Grounding with Complex Language Context (Bhathiya Hemanthage)

  • Towards a Real-Time Multimodal Emotion Estimation Model for Dialogue Systems (Jingjing Jiang)

  • Exploring Explainability and Interpretability in Generative AI (Shiyuan Huang)

  • Innovative Approaches to Enhancing Safety and Ethical AI Interactions in Digital Environments (Zachary Yang)

  • Leveraging Linguistic Structural Information for Improving the Model's Semantic Understanding Ability (Sangmyeong Lee)

  • Multi-User Dialogue Systems and Controllable Language Generation (Nicolas Wagner)

  • Enhancing Role-Playing Capabilities in Persona Dialogue Systems through Corpus Construction and Evaluation Methods (Ryuichi Uehara)

  • Character Expression and User Adaptation for Spoken Dialogue Systems (Kenta Yamamoto)

  • Interactive Explanations Through Dialogue Systems (Isabel Feustel)

  • Towards Emotion-aware Task-oriented Dialogue Systems in the Era of Large Language Models (Shutong Feng)

  • Utilizing Large Language Models for Customized Dialogue Data Augmentation and Psychological Counseling (Zhiyang Qi)

  • Toward More Human-like SDSs: Advancing Emotional and Social Engagement in Embodied Conversational Agents (Zi Haur Pang)

Roundtable 1 (Day 1)

 Topic 1: Multimodality

• Discuss the diverse aspects of multimodality in SDSs, including the utilization of visual information, environmental context, gestures, emotions, and personalization. Explore how these aspects can be effectively combined and what effect can be achieved.

• Chair: Yuki Zenimoto & Koji Inoue

 Topic 2: Data and Techniques

• Discuss the challenges and innovative approaches related to data creation, collection, and learning techniques for advanced SDSs, such as adaptation for unseen data, controllability, effective use of LLMs, and efficiency.

• Chair: Yahui Fu & Armand Stricker

 Topic 3: Evaluation

• Critically examine the current evaluation practices for SDSs and their limitations. Explore innovative automated evaluation metrics and methodologies for various domains, such as in non-task-oriented dialogues.

• Chair: Brielen Madureira & Atsumoto Ohashi

Roundtable 2 (Day 2)

 Topic 4: Explainability and Trustworthy

• Discuss the importance and methods of making SDSs more explainable and trustworthy, including the development of conversational explainable AI (XAI), the evaluation of reliability, the controllability of language generation, and dealing with closed proprietary models.

• Chair: Atsumoto Ohashi & Yuki Zenimoto

 Topic 5: Taking Inspiration from Human Cognition

• Explore how insights from human cognitive processes, language acquisition, and social interaction can inform the development of more advanced SDSs, including the integration of physiological signals and the development of collaborative and creative systems.

• Chair: Brielen Madureira & Armand Stricker

 Topic 6: Interdisciplinarity

• Discuss how we can foster collaboration between the fields of SDSs and other disciplines, such as linguistics, psychology, robotics, and social sciences. Explore the benefits and ways to incorporate insights from other fields into practical SGSs development.

• Chair: Koji Inoue & Yahui Fu

Roundtable 3 (Day 2)

 Topic 7: Present and Future of SDSs

• Critically think about the current directions in the SDSs field and the reasons and necessity for doing so. Discuss future research directions, including to what extent human-like SDSs are desirable and the ideal relationship between humans and SDSs.

• Chair: Atsumoto Ohashi & Yahui Fu

 Topic 8: Possibilities and limits of LLMs

• Discuss the capabilities and limitations of LLMs in the context of SDSs. Explore how to effectively incorporate LLMs into SDSs, such as architecture design, controllability, and handling of multimodal dialogues.

• Chair: Armand Stricker & Yuki Zenimoto

 Topic 9: Ethics and Safety

• Raise awareness about the ethical considerations and potential risks associated with the development and deployment of SDSs, such as when working with powerful but opaque models and creating human-like SDSs. Address concerns related to privacy, data rights, toxicity, and misinformation.

• Chair: Koji Inoue & Brielen Madureira