IWDS 2024

The 7th International Workshop on Dialog Systems

February 18 (Sunday), 2024, Bangkok, Thailand

In conjunction with the IEEE BigComp 2024 - 11th IEEE International Conference on Big Data and Smart Computing


When people look for information or find particular services, they used to put queries into search engines and choose a desired one among candidates. Although this way of human computer interaction (HCI) makes it possible to find their desired ones much efficiently than before, now they want more convenient way. Dialog system is the one, which makes people to communicate with computers through natural language or voices. The dialog system is successfully applied to various applications, such as intelligent speaker (e.g., Amazon echo, Google home) and intelligent counsellor, courtesy of great advance of machine learning techniques. It usually consists of several cascade steps (e.g., speech to text, natural language understanding), and it is necessary to find a way of improving of the steps and effectively incorporating them. We want to discuss and share the knowledge about how to solve these issues.

Theme, Purpose, and Scope

This workshop aims to create opportunities to discuss about the state-of-the-art studies, and to share on-going works. We hope that this will enhance collaboration among the researchers related to dialog systems. There are many challenging issues, such as out-of-domain detection, distant voice recognition, and end-to-end systems. We want to discuss about how to solve such issues, and share the experiences of applying the dialog system to real-world applications.

We invite submissions on topics that include, but are not limited to, the following:

  • Intelligent dialog systems
  • Chatbot systems
  • Speech recognition
  • Speech synthesis
  • Natural language understanding
  • Information extraction
  • Dialog management
  • Language resources and representation scheme for dialog systems

Organizing Committee

Workshop Co-chairs

  • Young-Seob Jeong (Chungbuk National University, Korea)
  • Chae-Gyun Lim (KAIST, Korea)
  • Jonghwan Hyeon (KAIST, Korea)
  • Ho-Jin Choi (KAIST, Korea)

Program Committee

  • KyungTae Lim (Seoul National University of Science and Technology, Korea)
  • Jihoon Moon (Soonchunhyang University, Korea)
  • Seok-Jun Buu (Gyeongsang National University, Korea)
  • Sunjae Kwon (University of Massachusetts Amherst, USA)
  • Sangjae Lee (Samsung Electronics Co., Ltd., Korea)
  • Han-Gyu Kim (Naver, Korea)
  • Cheoneum Park (SK Telecom, Korea)
  • Jingun Jung (Samsung Electronics Co., Ltd., Korea)
  • Young-Jun Lee (KAIST, Korea)
  • YunSeok Choi (Sungkyunkwan University, Korea)
  • Kyo-Joong Oh (KAIST, Korea)
  • Zae Myung Kim (University of Minnesota, Twins Cities, USA)
  • Won-Jo Lee (SAIT, Korea)
  • Jong Myoung Kim (SK Telecom, Korea)
  • Seung-Ho Han (KAIST, Korea)
  • Dongkun Lee (KAIST, Korea)
  • Yechan Hwang (KAIST, Korea)
  • Chan-Yong Park (SK Telecom, Korea)
  • Won-Deuk Yoon (Samsung Electronics Co., Ltd., Korea)
  • Namhyeok Kim (Colley Co., Ltd., Korea)


Generative AI for Education: New Impetus for Digital Transformation in Education


Jeongyun Han
Jeongyun Han
  • Associate Research Fellow, Ph.D.
  • Korean Educational Development Institute


The advancement of technology is influencing various sectors of society, including education. Particularly, the rapidly evolving field of generative AI is gaining attention as a key technology for addressing educational challenges and fostering innovation in education. However, like most technologies, generative AI also encompasses potential limitations, which could pose obstacles in its application for educational purposes. This session aims to discuss how advanced technology can overcome these barriers and be effectively implemented in the field of education.


Jeongyun Han serves as an Associate Research Fellow at the Korean Educational Development Institute (KEDI). His research primarily centers on leveraging educational data and AI to enhance learning environments and shape the future of education. He holds a deep interest in identifying the role of AI in facilitating personalized education within technology-enhanced learning contexts. Recently, he has been involved in research focused on generating personalized feedback through the use of generative AI.


09:30 - 16:30, February 18 (Sunday), 2024

• Venue: Kamolrudi (2F, The Sukosol Hotel, Bangkok)

Part 1: Dialog Systems

※ Authors have to prepare 15 min. for their presentation (including 5 min. for Q&A).

09:30 - 10:50 Session 1: Chatbots and Natural Language Understanding

(Session Chair: Chae-Gyun Lim (KAIST, Korea))

  • Prompting Large Language Models for Automatic Evaluation on User-specific Memory Extraction
  • Chae-Gyun Lim (KAIST, Korea)
  • DialogCC: An Automated Pipeline for Creating High-Quality Multi-modal Dialogue Datasets
  • Young-Jun Lee (KAIST, Korea)
  • Enhancing Numerical Reasoning Performance by Augmenting Distractor Numerical Values
  • Ye-Chan Hwang (KAIST, Korea)
  • Enhancing Knowledge Selection with Data Processing Based on Multiple Turns of Dialog in Knowledge-Grounded Open-Domain Conversations
  • Eojin Joo (KAIST, Korea)
  • Reducing Argument Misrecognition in Quantitative Question Answering
  • Jinsu Lim (KAIST, Korea)
  • Coffee Break

11:00 - 12:30 Session 2: Information Extraction and Intelligent Applications

(Session Chair: Jonghwan Hyeon (KAIST, Korea))

  • Research on the AI Personality
  • Young-Seob Jeong (Chungbuk National University, Korea)
  • Refining Saliency Maps Using Gaussian Mixture Model
  • Seung-Ho Han (KAIST, Korea)
  • Machine Fault Diagnosis Using EMD-Gammatone Texture Representation and A Lightweight Self-Attention SqueezeNet
  • Mahe Zabin (KAIST, Korea)
  • Enhanced Deep Electric Pole Anomaly Detection Using Generative Adversarial Network-based Data Augmentation
  • Dongkun Lee (KAIST, Korea)
  • Improving Speech Emotion Recognition via Segmental Average Pool
  • Jonghwan Hyeon (KAIST, Korea)
  • Lunch Break

Part 2: Generative AI and Education

14:00 - 15:00 Keynote Speech

(Session Chair: Young-Seob Jeong (Chungbuk National University, Korea))

  • Generative AI for Education: New Impetus for Digital Transformation in Education (50 min. + Q&A 10 min.)
  • Jeongyun Han (Korean Educational Development Institute, Korea)
  • Coffee Break

15:15 - 17:00 Panel Discussion

(Session Chair: Chae-Gyun Lim (KAIST, Korea))

  • Educational Influence of Generative AI Technologies
  • • Moderator: Ho-Jin Choi (KAIST, Korea)
    • Panelist: Young-Seob Jeong (Chungbuk National University, Korea), Yuchae Jung (Open Cyber University of Korea, Korea), Jeongyun Han (Korean Educational Development Institute, Korea)
  • Closing Remarks


All questions about submissions should be emailed to chairs Chae-Gyun Lim (rayote@kaist.ac.kr) or Young-Seob Jeong (ysjay@chungbuk.ac.kr).