First Call for Papers
Organizers: Heuiseok Lim, Seungryong Kim, Yeonsoo Lee, Steve Lin, Paul Hongsuck Seo, Yumin Suh
Humans usually have conversations by making use of prior knowledge about a topic and background information of the people whom they are talking to. However, existing conversational agents and datasets do not consider such comprehensive information, and thus they have a limitation in generating the utterances where the knowledge and persona are fused properly.
In our workshop on Customized Chat Grounding Persona and Knowledge, researchers and students will share their prospects and latest discoveries. We also host new shared tasks with the new dataset called FoCus (call For Customized conversation) where the customized answers are built with the user's persona and Wikipedia knowledge.
We encourage submissions from a wide range of topics, including but not limited to:
· Persona-grounded dialogue systems
· Knowledge-grounded dialogue systems
· Machine Reading Comprehension with Persona or Knowledge
· Task-oriented knowledge-grounded multimodal dialogue
· Evaluations for knowledge-grounded dialogue
· Evaluations for persona-grounded dialogue
You also can join our shared task track: https://codalab.lisn.upsaclay.fr/competitions/3754#learn_the_details
Shared task track aims to build a customized and intelligent conversational agent. In particular, the conversational agent takes the role of providing knowledgeable answers according to the user's background information. It consists of two sub-tasks, predicting which persona and knowledge are needed to answer the question and generating plausible answers.
Information for Authors
We invite papers on original, unpublished work in the topic areas of the workshop. In addition to (1) long papers, (2) short papers we will consider (3) presentation as well.
1) Long papers, presenting completed work, may consist of up to eight (8) pages of content plus additional pages of references (just two if possible). The final camera-ready versions of accepted long papers will be given one additional page of content (up to 9 pages) so that reviewers’ comments can be taken into account.
2) Short papers / demo presenting work in progress, or the description of a system, and may consist of up to four (4) pages of content plus additional pages of references (one if you can). Upon acceptance, short papers will be given five (5) content pages in the proceedings.
3) Technical report presentation without paper can be presented and discussed at our workshop.
1) long papers and 2) short papers are to use the ACL stylesheets adopted by COLING 2022 (for LaTeX, MS Word or Overleaf). Papers should be submitted electronically, in
PDF, at our submission system: https://www.softconf.com/coling2022/CCGPK/.
Reviewing will be double-blind. Please do not include the authors’ names and affiliations, or any references to Websites, project names, acknowledgements and so on — anything that immediately reveals the authors’ identity. Self-references should be kept to a reasonable minimum, and anonymous citations cannot be used.
Beside papers, we also invite 3) technical report presentation without paper. You can share your presentation with attendees about your current research. If you want to present your technical report, please send us an email: pkchat.focus@gmail.com
Important Dates (tentative)
Papers due: July 11, 2022 (Anywhere On Earth)
Notification of acceptance: August 22, 2022
Camera-ready papers due: September 5, 2022 (Anywhere On Earth)
Workshop: one day in the period October 12-17, 2022
More on the organizers:
Heuiseok Lim, Korea University, Republic of Korea
Seungryong Kim, Korea University, Republic of Korea
Yeonsoo Lee, Language AI Lab, NCSOFT, Republic of Korea
Steve Lin, Microsoft Research Asia, China
Paul Hongsuck Seo, Google Research, United States
Yumin Suh, NEC Labs, United States
Contact:
Related paper: