IWDS 2022

The 5th International Workshop on Dialog Systems

January 17 (Monday), 2022, Daegu, Korea

In conjunction with the IEEE BigComp 2022 - 9th IEEE International Conference on Big Data and Smart Computing

Welcome to IWDS 2022

NOTE: Considering the situation of COVID-19 pandemic, each presentation can be done in video or Zoom.

Zoom Meeting Information
 - Direct Access URL: https://us06web.zoom.us/j/84080035487?pwd=SWNZcERUWEZZTW9uRExPdWcxdTFOdz09
 - Meeting ID: 840 8003 5487
 - Meeting Pw: 2022iwds
• Authors have to attend this Zoom meeting at the beginning of the workshop. If some presentations are done early, then we may move to the next presentation.

Motivation

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

Paper Submission

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: https://easychair.org/my/conference?conf=iwds2022

Paper templates:
IEEE_MSWord_Template.doc
IEEE_Latex_Template.zip


Important Dates

Submission of Workshop Papers
November 12, 2021   (Final Extended) November 26, 2021 (UTC -12)
Notification of Paper Acceptance
December 1, 2021
Camera Ready Submission
December 7, 2021
Author Registration
December 18, 2021
Workshop
January 17, 2022

Organizational Committee

Organizing Committee

  • Chae-Gyun Lim (KAIST, Korea)
  • Young-Jun Lee (KAIST, Korea)
  • Ho-Jin Choi (KAIST, Korea)

Program Committee

  • Young-Seob Jeong (Chungbuk National University, Korea)
  • KyungTae Lim (Hanbat National University, Korea)
  • Cheoneum Park (AIRS Company, Hyundai Motor Group, Korea)
  • Sunjae Kwon (University of Massachusetts Amherst, USA)
  • Han-Gyu Kim (Naver, Korea)
  • YunSeok Choi (Sungkyunkwan University, Korea)
  • Kyo-Joong Oh (KAIST, Korea)
  • Jonghwan Hyeon (KAIST, Korea)
  • Zae Myung Kim (Naver Labs Europe, France)
  • Joohee Park (Naver, Korea)
  • 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, Korea)
  • Jong-Min Park (Twinny, Korea)

Invited Talk

The Power of Visualization: English Language Learners in Transformation

Speaker

So-Yeon Ahn
So-Yeon Ahn
  • Assistant Professor
  • School of Humanities and Social Sciences, KAIST
  • [Profile]

Abstract

The presentation examines to uncover how English learners make sense of themselves in relation to English and how they view the impact of English on their future lives. In doing so, the study pays attention to how the interplay of fear and desire plays a role in the imagination of English learners’ future, and in the construction of accessible and imagined communities. The study employs a multimodal analytical framework to uncover how multiple modes including both the graphic representations and written narratives are orchestrated to establish symbolic and representative values. The findings yield insight into the combination of visual and verbal means of data collection and analysis in gaining a deeper understanding of learner perspectives, attitudes, and beliefs.

Bio

So-Yeon Ahn is an assistant professor at KAIST (Korea Advanced Institute of Science and Technology), where she conducts research on and social and cultural approaches to language learning, language play and awareness, and intercultural communicative competence. She is particularly interested in the multimodal analysis of language teacher and language learner identity construction and societal ideologies. Her recent work has appeared in Language Awareness, Applied Linguistics Review, and System. Currently, she serves as a member of the boards of directors for Applied Linguistics Association of Korea and Modern English Education Society, and a member of the editorial review board of the Journal of Language, Identity, and Education.


Program

※ Authors have to prepare 25 min. for their presentation (including 5 min. for Q&A).

13:20 - 17:35, January 17 (Monday), 2022 (Korea Standard Time, UTC+9)

13:20 - 13:25
Welcoming Address
13:25 - 14:15
[Invited Talk] The Power of Visualization: English Language Learners in Transformation
So-Yeon Ahn (School of Humanities and Social Sciences, KAIST)
14:15 - 14:25
Coffee Break
14:25 - 14:50
The Text Analysis Framework for Interactive Statistical Classification Service
Kyo-Joong Oh, Ho-Jin Choi, Jinwon Kim, Wonsoek Cha and Kyungmin Lim
14:50 - 15:15
Boosting Adapter Transfer Learning via Weak Parameter Sharing
June Suk Choi, Chae-Gyun Lim and Ho-Jin Choi
15:15 - 15:40
Exploring the Repetition Problem in Empathetic Dialogue Generative Model
Young-Jun Lee and Ho-Jin Choi
15:40 - 16:05
Data Stream Classification by Using Stacked CARU Networks
Ka-Hou Chan and Sio-Kei Im
16:05 - 16:15
Coffee Break
16:15 - 16:40
Toward Robust Response Selection Model for Cross Negative Sampling Condition
Nyoungwoo Lee and Ho-Jin Choi
16:40 - 17:05
Knowledge Management Approach for Memory Components Based on User-friendly Conversational System
Chae-Gyun Lim, Dongkun Lee, Young-Jun Lee and Ho-Jin Choi
17:05 - 17:30
Checklist for Validating Trustworthy AI
Seung-Ho Han and Ho-Jin Choi
17:30 - 17:35
Closing Remarks

Contact

All questions about submissions should be emailed to chairs Chae-Gyun Lim (rayote@kaist.ac.kr) or Young-Jun Lee (passing2961@gmail.com).