***SummDial @ SIGDial 2021: A Special Session on Automatic Minuting and Summarization of Dialogues and Multi-party Meetings*** https://elitr.github.io/automatic-minuting/summdial.html ***Overview*** With a sizeable working population of the world going virtual, resulting in information overload from multiple online meetings, imagine how convenient it would be to just hover over past calendar invites and get concise summaries of the meeting proceedings? How about automatically minuting a multimodal multi-party meeting? Are minutes and multi-party dialogue summaries the same? We believe Automatic Minuting is challenging. There are possibly no agreed-upon guidelines to take minutes, and people adopt different styles to record minutes of the meeting. The minutes also depend on the meeting's category, the intended audience, and the goal or objective of the meeting. The SummDial special session at SIGDial 2021 intends to instigate discussions on these challenges. Our goal for this SIGDial special session would be to stimulate intense discussions around this topic and set the tone for further interest, research, and collaboration in both Speech and Natural Language Processing communities. We are also launching a shared task on Automatic Minuting (AutoMin) at Interspeech 2021: https://elitr.github.io/automatic-minuting/ ***SummDial @ SIGDial 2021 will be an all-virtual event*** ***Call for Papers (Long, Short, Late-breaking, Research In Progress, Position Papers)*** We invite regular and work-in-progress papers that report: - Current research in multi-party dialogue summarization for summarizing meetings, spoken dialogue, using speech, text, or multi-modal data (audio, video), - Challenges in manual and automatic dialogue summarization evaluation, - New methods and metrics for manual and automatic dialogue summarization evaluation, - Challenges and methods in summarizing transcripts in different domains, including legal, educational, political, social, etc. - Datasets and corpora for dialogue summarization, - Techniques of data collection, pre-processing, adaptation, - Ethical issues and possible solutions, - New systems for dialogue or meeting summarization, or new evaluations of existing systems, - Qualitative or quantitative comparisons of speech-specific summarization systems and summarization systems imported from the text domain, - Tools for meeting transcript generation and automatic summarization, - Topic detection and span identification in meeting transcripts for multi-topic summarization, - Position papers to reflect on the current state of the art in this topic, take stock of where we have been, where we are, where we are going and where we should go. Researchers may choose to submit: - ***Long papers*** must describe substantial, original, completed, and unpublished work. Wherever appropriate, concrete evaluation and analysis should be included. These papers would go through the same peer-review process by the SIGDial program committee as papers submitted to the main SIGdial track. These papers will appear in the main SIGdial proceedings and are presented with the main track. Long papers must be no longer than 8 pages, including title, text, figures, and tables. An unlimited number of pages is allowed for references. Two additional pages are allowed for appendices containing sample discourses/dialogues and algorithms, and an extra page is allowed in the final version to address reviewers’ comments. - ***Short papers*** must describe original and unpublished work. These papers would go through the same peer-review process by the SIGDial program committee as papers submitted to the main SIGdial track. These papers will appear in the main SIGdial proceedings and are presented with the main track. Please note that a short paper is not a shortened long paper. Instead, short papers should have a point that can be made in a few pages, such as a small, focused contribution; a negative result; or an interesting application nugget. It should be no longer than 4 pages, including title, text, figures, and tables. An unlimited number of pages is allowed for references. One additional page is allowed for sample discourses/dialogues and algorithms, and an extra page is allowed in the final version to address reviewers’ comments. An unlimited number of pages are allowed for references. - ***Late-breaking and Work-in-progress papers*** will showcase ongoing work and focused relevant contributions. Submissions need not present original work. Late-breaking and work-in-progress papers should be no longer than four pages, including title, text, figures and tables, and references. These will be reviewed by the SummDial program committee and posted on the special session website. These papers will be presented as lightning talks or posters during the session. Authors will retain the copyright to their work so that they may submit it to other venues as their work matures. - ***Position papers*** will give voice to authors who wish to take a position on a topic listed above or the field of spoken, dialogue, meeting summarization. Submissions need not present original work and should be two to six pages in length, including title, text, figures and tables, and references. These will be reviewed by the SummDial program committee and posted on the special session website. These papers will be presented as lightning talks or posters during the session. Authors will retain the copyright to their work so that they may submit it to other venues. ***Papers submitted to the SummDial special session by the SIGDial 2021 submission deadline (April 2/April 10) would be reviewed by the SIGDial 2021 program committee and included within the SIGDial 2021 proceedings upon acceptance. Papers submitted by the later deadline (May 31) will be reviewed by the SummDial program committee. Upon acceptance, they could be archived on ISCAarchive or the authors may choose to be non-archival and submit their work to some other venues later.*** ***SummDial Special Session*** The special session would consist of a keynote, a panel, lightning talks, oral and poster paper presentations. Details of the program would be updated on our website: https://elitr.github.io/automatic-minuting/summdial.html ***Keynote Speaker*** TBA ***Panel Discussion*** Topic: Challenges to Automatic Minuting, Meeting and Multi-party Dialogue Summarization- Taking Stock, and Looking Ahead Panelist 1: Prof. Ani Nenkova, Associate Professor, University of Pennsylvania Panelist 2: Prof. Diyi Yang, Assistant Professor, School of Interactive Computing, Georgia Tech. Panelist 3: TBA Panelist 4: TBA Panelist 5: TBA Moderator: Prof. Ondřej Bojar, Institute of Formal and Applied Linguistics, Charles University, Czech Republic ***Important Dates*** - Regular Papers (Long and Short) Abstract Deadline (SIGDial)*: April 2, 2021 - Regular Papers (Long and Short) Deadline (SIGDial): April 10, 2021 - Notification for Regular Papers: May 24, 2021 - Camera-ready due (Regular Papers): June 8, 2021 - Late-breaking (LBR), Position, and Work-In-Progress Papers (WiP) Deadline: May 31, 2021 - Notification for LBR/WiP/Position Papers: July 5, 2021 - Event date: TBA (between July 29 - 31, 2021) *It is mandatory to submit a placeholder abstract by April 2nd and do the final paper submission on April 10th for SIGDial 2021. All submission deadlines are 23:59 GMT-11 ***Submission Website and Format*** - For Regular Papers (Long and Short), please follow the SIGDial 2021 submission instructions http://www.colips.org/conferences/sigdial2021/wp/call-for-papers/ - SummDial at SIGDial 2021 submission website: https://www.softconf.com/l/sigdial2021/ - For Late-breaking, Work-In-Progress, and Position Papers, please submit to minute@ufal.mff.cuni.cz - Please follow SIGDial 2021 submission instructions and formatting guidelines. ***Organizers*** - Tirthankar Ghosal, Charles University, Czech Republic - Muskaan Singh, Charles University, Czech Republic - Anja Nedoluzhko, Charles University, Czech Republic - Ondřej Bojar, Charles University, Czech Republic ***Contact:*** ghosal@ufal.mff.cuni.cz ***Website:*** https://elitr.github.io/automatic-minuting/summdial.html -- +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ Tirthankar Ghosal <https://tirthankarslg.wixsite.com/ainlpmldl> Visvesvaraya Research Fellow <http://meity.gov.in/esdm/phd-scheme> Elsevier Center of Excellence for Natural Language Processing <http://www.iitp.ac.in/~ai-nlp-ml/collaboration.html> Department of Computer Science and Engineering Indian Institute of Technology Patna <http://www.iitp.ac.in/> +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++