February 21-24, 2023

IWSDS 2023

Los Angeles, USA

University of Southern California Institute for Creative Technologies

Detailed Schedule:


Tuesday, 21 February 2023

 

08:15 Registration opens, coffee and tea


09:00-13:00 Workshop: Language-Based AI Agent Interaction with Children (check the workshop’s website https://aichildinteraction.github.io/ for the schedule)

 

13:00-14:00 Lunch

 

14:00-14:20 IWSDS Opening

 

14:20-15:20 Keynote Talk: Phil Cohen (Session Chair: David Traum)

 

15:20-15:50 Break

 

15:50-17:30 Oral Session 1 (Session Chair: M. Inés Torres)

15:50-16:10 An investigation on how zero-shot slot filling benefits the task-oriented dialogue system – Sixia Li and Shogo Okada (virtual)

paper pdf

 

16:10-16:30 Clarifying characteristics of dialogue summary in dialogue format – Sanae Yamashita and Ryuichiro Higashinaka

paper pdf

 

16:30-16:50 GraphWOZ: Dialogue Management with Conversational Knowledge Graphs – Nicholas Thomas Walker, Stefan Ultes and Pierre Lison

paper pdf

 

16:50-17:10 Learning to quide questions in chat-oriented dialogue by using combination of question-guiding corporaSota Horiuchi and Ryuichiro Higashinaka

paper pdf

 

17:10-17:30 Effective Dialogue-Context Retriever for Long-Term Open-Domain Conversation – Meguru Takasaki, Naoki Yoshinaga and Masashi Toyoda

paper pdf

 

17:30-18:30 Poster Session

Analysis of Face Acts in Japanese Multimodal Persuasive Dialogue Corpus – Seiya Kawano, Hideko Habe, Akishige Yuguchi and Koichiro Yoshino

paper pdf    poster pdf

 

Semi-autonomous Guide Agents with Simultaneous Handling of Multiple Users – Yusuke Muraki, Haruki Kawai, Kenta Yamamoto, Koji Inoue, Divesh Lala and Tatsuya Kawahara

paper pdf

 

The prosodic expressions of negative micro-sentiment vary across corpora – Dimitri E. Lyon and Nigel G. Ward

paper pdf    poster pdf

 

Batch-level  GANs to promote dialogue response variety – Asier López Zorrilla, Alain Vázquez and M. Inés Torres

paper pdf    poster pdf

 

Modeling Multiple User Interests using Hierarchical Knowledge for Conversational Recommender System – Yuka Okuda, Katsuhito Sudoh, Seitaro Shinagawa and Satoshi Nakamura

paper pdf    poster pdf

 

Improving Empathetic Response Generation with Retrieval based on Emotion Recognition – Yahui Fu, Koji Inoue, Divesh Lala, Kenta Yamamoto, Chenhui Chu and Tatsuya Kawahara

paper pdf    poster pdf

 

Investigation of Naming in Process of Building Common Ground through Collaborative Dialogues – Yu Saito, Koh Mitsuda, Ryuichiro Higashinaka and Yasuhiro Minami

paper pdf    poster pdf

 

MEM-BERT: Masked Entity Model-Based Transformers for Realtime Personalization Qingxiaoyang Zhu, Nehal Bengre and Tapas Kanungo

paper pdf    poster pdf

 

First Impressions Matter: A Voice Assistant Study Using Log-Based Predictive Metrics – Tapas Kanungo, Nehal Bengre, Stephen Walsh, Qingxiaoyang Zhu and Dmitrii Siakov

paper pdf    poster pdf

 

Towards integrating eye gaze tracking into a multimodal dialog agent for remote patient assessment – Daniel Tisdale, Jackson Liscombe, David Pautler and Vikram Ramanarayanan (demo)

paper pdf    poster pdf

 

Voice Assistant Accessibility – Angus Addlesee

paper pdf    poster pdf

 

A Transformer-based Response Evaluator for Open-Domain Spoken Conversation – Davan Harrison, Rishi Rajasekaran and Marilyn Walker

paper pdf

 

18:30 Reception

 

 

Wednesday, 22 February 2023

 

08:15 Registration opens, coffee and tea


09:00-10:00 Keynote Talk: Ryuichiro Higashinaka (Session Chair: Koichiro Yoshino)

 

10:00-10:30 Break

 

10:30-12:40 Special Session: Multi-Party Conversational AI (Session Chairs: Weronika Sieińska and Angus Addlesee)

10:30-10:35 Introduction

 

10:35-10:55 FCC: Fusing Conversation History and Candidate Provenance for Contextual Response Ranking in Dialogue Systems – Zihao Wang, Eugene Agichtein and Jinho Choi (virtual)

paper pdf

 

10:55-11:15 Data Collection for Multi-party Task-based Dialogue in Social Robotics – Angus Addlesee, Weronika Sieińska, Nancie Gunson, Daniel Hernández García, Christian Dondrup and Oliver Lemon

paper pdf

 

11:15-11:35 Comparing Multi-User Interaction Strategies in Human-Robot Teamwork – Nicolas Wagner, Matthias Kraus, Niklas Lindemann and Wolfgang Minker

paper pdf

 

11:35-11:55 Dependency Dialogue Acts — Annotation Scheme and Case Study – Jon Z. Cai, Brendan King, Margaret Perkoff, Shiran Dudy, Jie Cao, Marie Grace, Natalia Wojarnik, Ananya Ganesh, James H. Martin, Martha Palmer, Marilyn Walker and Jeffrey Flanigan

paper pdf

 

11:55-12:40 Panel Panelists: Angus Addlesee, Jeffrey Flanigan, Nicolas Wagner, Zihao Wang (Moderator: Weronika Sieińska)

 

12:40 Lunch, Cultural Activity, and Banquet

 

 

Thursday, 23 February 2023

 

08:15 Registration opens, coffee and tea


09:00-10:40 Oral Session 2 (all presentations in this session are virtual) (Session Chair: Ron Artstein)

09:00-09:20 Factors in Crowdsourcing for Evaluation of Complex Dialogue Systems – Annalena Aicher, Stefan Hillmann, Isabel Feustel, Thilo Michael, Sebastian Möller and Wolfgang Minker (virtual)

paper pdf

 

09:20-09:40 Fostering User Engagement in the Critical Reflection of Arguments – Klaus Weber, Annalena Aicher, Wolfgang Minker, Stefan Ultes and Elisabeth André (virtual)

paper pdf

 

09:40-10:00 The Importance of Data Diversity for Engagement Recognition Systems: a Cross-cultural Study – Denis Dresvyanskiy, Alexey Karpov and Wolfgang Minker (virtual)

paper pdf

 

10:00-10:20 Modeling Speaker-Listener Interaction for Backchannel Prediction – Daniel Ortega, Sarina Meyer, Antje Schweitzer and Ngoc Thang Vu (virtual)

paper pdf

 

10:20-10:40 Investigating Reinforcement Learning for Communication Strategies in a Task-Initiative Setting – Baber Khalid and Matthew Stone (virtual)

paper pdf

 

10:40-11:10 Break

 

11:10-12:10 Keynote Talk: Marilyn Walker (Session Chair: Kallirroi Georgila)

 

12:10-13:10 Lunch

 

13:10-14:50 Oral Session 3 (Session Chair: Nigel Ward)

13:10-13:30 Improving Open-Domain Dialogue Evaluation with a Causal Inference Model – Cat P. Le, Luke Dai, Michael Johnston, Yang Liu, Marilyn Walker and Reza Ghanadan

paper pdf

 

13:30-13:50 Module Selection: A new task for Dialog Systems – Jan Nehring, Akhyar Ahmed and Lena A. Jäger

paper pdf

 

13:50-14:10 Understanding the Effectiveness of Very Large Language Models on Dialog Evaluation – Jessica Huynh, Cathy Jiao, Prakhar Gupta, Shikib Mehri, Payal Bajaj, Vishrav Chaudhary and Maxine Eskenazi

paper pdf

 

14:10-14:30 How Should We Represent Dialog Acts to Leverage Pretrained Natural Language Generators? – Alain Vázquez, Asier López Zorrilla and M. Inés Torres

paper pdf

 

14:30-14:50 Towards interactive explanations of machine learning methods through dialogue systems – Isabel Feustel, Niklas Rach, Wolfgang Minker and Stefan Ultes

paper pdf

 

14:50-15:20 Break

 

15:20-17:00 Oral Session 4 (Session Chair: Stefan Ultes)

15:20-15:40 Impact of synthetic voice and avatar animation on the usability of a dialogue agent for digital health monitoring – Hardik Kothare, Doug Habberstad, Michael Neumann, Sarah White, David Pautler and Vikram Ramanarayanan (virtual)

paper pdf

 

15:40-16:00 Pathology-specific settings for voice activity detection in a multimodal dialog agent for digital health monitoring – Jackson Liscombe, Hardik Kothare, Michael Neumann, David Pautler and Vikram Ramanarayanan

paper pdf

 

16:00-16:20 Let’s Get Personal: Personal Questions Improve SocialBot Performance in the Alexa Prize – Kevin K. Bowden and Marilyn Walker

paper pdf

 

16:20-16:40 Controlling Personality Style in Dialogue with Zero-Shot Prompt-Based LearningAngela Ramirez, Mamon Alsalihy, Kartik Aggarwal, Cecilia Li, Liren Wu and Marilyn Walker

paper pdf

 

16:40-17:00 Character adaptation of spoken dialogue systems based on user personalities – Kenta Yamamoto, Koji Inoue and Tatsuya Kawahara

paper pdf

 

17:00-17:30 Break

 

17:30-18:30 Panel: Diversity in Dialogue

      Panelists: Jackson Liscombe, Marilyn Walker, Nigel Ward (Moderator: Koichiro Yoshino)

 

 

Friday, 24 February 2023

 

08:45 Registration opens, coffee and tea


09:30-10:50 Special Session: Dialogue Systems for Multilingual and Under-resourced Language Speakers (Session Chairs: A.Seza Doğruöz and Sunayana Sitaram)

09:30-09:50 Language-agnostic Code-Switching in Sequence-To-Sequence Speech Recognition – Enes Yavuz Ugan, Christian Huber, Juan Hussain and Alexander Waibel

paper pdf

 

09:50-10:10 Language portability strategies for open-domain dialogue with pre-trained language models from high to low resource languages – Ahmed Njifenjou, Virgile Sucal, Bassam Jabaian and Fabrice Lefèvre

paper pdf

 

10:10-10:20 Developing a spoken dialogue system for the Choctaw language Jacqueline Brixey and David Traum (demo)

 paper pdf      

 

10:20-10:50 Panel – Panelists: Jacqueline Brixey, Ahmed Njifenjou, Enes Yavuz Ugan (Moderator: A.Seza Doğruöz)


 

10:50-11:20 Break

 

11:20-12:20 Panel: ChatGPT and Future Directions

      Panelists: M. Inés Torres, David Traum, Stefan Ultes (Moderator: Kallirroi Georgila)

 

12:20-12:40 Conference Conclusion

 

12:40 Lunch (To Go)