The 4th International Workshop on Dialog Systems
(IWDS 2021)


The 4th International Workshop on Dialog Systems (IWDS 2021)

January 17, 2021, Bangkok, Thailand Jeju Island, Korea (Online)

In conjunction with the IEEE BigComp 2021 - 8th IEEE International Conference on Big Data and Smart Computing

NOTE: Presentations can be done in offline, video, or Zoom. (That is, all the offline presentations will be transmitted to the online site in real-time for online participants).


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


All papers must be original and not simultaneously submitted to another journal or conference. Prospective authors are invited to submit their papers, 4 pages, in English according to the IEEE two-column format for conference proceedings. The author list may appear in the paper, but can be omitted if the authors want to. The direct link for paper submission is below. All submissions will be peer-reviewed by the Program Committee of the workshop. All accepted workshop papers will be published in the IEEE Xplore Digital Library as conference proceedings.

Direct link for paper submission:

Paper templates:


Submission of Workshop Papers
September 30, 2020 November 10, 2020 November 16, 2020 (UTC -12)
Notification of Paper Acceptance
November 23, 2020 November 26, 2020
Camera Ready Submission
December 7, 2020
Author Registration
December 14, 2020
January 17, 2021


Organizing Committee

  • Chae-Gyun Lim, Ph.D Candidate, (KAIST, Korea)
  • Jonghwan Hyeon, Ph.D Candidate, (KAIST, Korea)
  • Young-Seob Jeong, Professor, (Soonchunhyang University, Korea)
  • Qiang Ma, Professor, (Kyoto University, Japan)
  • Ho-Jin Choi, Professor, (KAIST, Korea)

Program Committee

  • Sheng Li, Researcher (NICT, Japan)
  • Takayuki Yumoto, Professor (University of Hyogo, Japan)
  • Jianwei Zhang, Professor (Iwate University, Japan)
  • Jiyoung Woo, Professor (Soonchunhyang University, Korea)
  • Dongkun Lee, Researcher (KAIST, Korea)
  • Seung-Ho Han, Researcher (KAIST, Korea)
  • Zae Myung Kim, Researcher (NAVER LABS Europe, France)


Introduction on End-to-end Speech Recognition with Language Models


Han-Gyu Kim
Han-Gyu Kim
  • Researcher, Naver


Han-Gyu Kim received the B.S. degree in Department of Electronic Engineering, Tsinghua University, Beijing, China, in 2009, and the M.S. degree and the Ph.D degree in School of Computing, KAIST, Daejeon, South Korea, in 2011 and 2018, respectively. He has been a research engineer in NAVER Corp., Gyeonggi-do, South Korea since 2018. His research interests include speech recognition, source separation, machine learning and artificial intelligence.


09:00 - 12:05, January 17 (Sunday), 2021 (UTC+9)

09:00 - 09:05
Welcoming address
Young-Seob Jeong
09:05 - 09:55
Invited talk: Introduction on End-to-end Speech Recognition with Language Models
Han-Gyu Kim
09:55 - 10:00
Coffee break

Session 1 (10:00 - 12:05, Chair: Chae-Gyun Lim)

10:00 - 10:25
QUARC: Quaternion Multi-Modal Fusion Architecture For Hate Speech Classification
Deepak Kumar, Nalin Kumar, and Subhankar Mishra
10:25 - 10:50
Text Style Transfer Using DRG Framework of Combined Retrieval Strategy
Na-Dan Hong, Qiang Ma, and Young-Seob Jeong
10:50 - 11:15
Comparative Study of Emotion Annotation Approaches in Korean Dialogue
Young-Jun Lee, and Ho-Jin Choi
11:15 - 11:40
Pattern-Wise Embedding System for Scalable Time-series Database
Changha Lee, Seong-Hwan Kim, and Chan-Hyun Youn
11:40 - 12:05
A Framework of Callbot for Dialogue Process in Seperated Network
Kyo-Joong Oh, Jiha Song, Hweongak An, and Ho-Jin Choi
12:05 - 13:45

Session 2 (13:45 - 14:40, Chair: Jonghwan Hyeon)

13:45 - 14:10
A Modular Data-Driven Architecture for Empathetic Conversational Agents
Vincenzo Scotti, Roberto Tedesco, and Licia Sbattella
14:10 - 14:35
Generating Temporal Relation Candidates Based on Open-domain Relation in Clinical Notes
Chae-Gyun Lim, and Ho-Jin Choi
14:35 - 14:40
Closing remarks
Jonghwan Hyeon


All questions about submissions should be emailed to chairs Chae-Gyun Lim ( or Jonghwan Hyeon (