[iva] SigDial21 Special Session on SafeConvAI

[Rieser, Verena]

***SafeConvAI @ SIGDial 2021: A Special Session on Safety for E2E Conversational AI***
https://sites.google.com/view/safety4convai/home

***Overview***
Recent progress in end-to-end (E2E) open-domain dialogue agents (aka Conversational AI) has shown a dramatic improvement in the ability of these models to learn patterns and mimic conversational behaviours from the training data. Unfortunately, these models still exhibit many concerning problems. First, they may learn undesirable features present in the training data such as biased, toxic, or otherwise harmful language. Second, they do not respond reliably in safety critical situations, such as the user asking for medical advice, indicating intention of self-harm, or during public health crises such as COVID-19. Third, they are susceptible to adversarial attacks for personal information, posing significant risk to those whose data they are trained on.
These problems are difficult, as what is deemed as “offensive” or even “sensitive” is both contextually and culturally dependent and picking up on more subtle examples of unsafe language often requires a level of language understanding that is well beyond current capabilities.
A first workshop was held to discuss these topics in October 2020 (https://safetyforconvai.splashthat.com/). Following on from that, this special session will take place at SIGDial 2021.

***SafeConvAI Special Session @ SIGDial 2021 will be an all-virtual event***
The special session will consist of a keynote (TBA), a panel, lightning talks, oral and poster paper presentations. Details of the program will be announced via our website: https://sites.google.com/view/safety4convai/home

***Call for Papers (Long, Short, Late-breaking, Research In Progress, Position Papers)***
We invite regular and work-in-progress papers that report:

  *   Current research on identifying and/or preventing dialogue models from generating messages containing hate speech, pornographic or sexual content, offensive or profane language, medical or self-harm advice, privacy leaks, or otherwise harmful behaviour.
  *   Work on understanding how social bias is embedded in conversational AI and conversational agents, and approaches to mitigate the harms of such biases,
  *   Qualitative or quantitative investigations on strategies for how models should best respond to various types of unsafe content,
  *   Relevant work in related fields, including HRI, virtual agents, etc.
  *   New methods and metrics for evaluating the relative safety of conversational AI models,
  *   New (dynamic) benchmarks and datasets to investigate these issues,
  *   Dataset releases that address current biases or imbalances in data used to train/evaluate dialogue systems,
  *   Conversational abuse detection and mitigation across multiple languages, dialects, and sociolects; spoken and typed interactions etc., this includes abusive, derogatory, or otherwise harmful speech, including but not limited to: bullying, micro-aggressive behaviour, toxic language, hate speech and offensive language.
  *   Reliably and robustly detecting safety critical situations,
  *   Related issues including privacy and privacy leaks, persona-design, fairness, accessibility, and inclusion for Conversational AI systems,
  *   Best practices for researching and releasing E2E conversational AI,
  *   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.

Submission format:
- ***Long papers*** must describe substantial, original, completed, and unpublished work. Wherever appropriate, concrete evaluation and analysis should be included. These papers will undergo 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 abstracts*** will showcase ongoing work and focused relevant contributions. Submissions need not present original work. Late-breaking and work-in-progress abstracts should be no longer than 1 page. The submissions will be reviewed by the SafeConvAI program committee and posted on the special session website. Abstracts will be presented as lightning talks and/or posters during the session. Authors will retain the copyright to their work so that they may submit to other venues as their work matures.

***Important Dates***
- Regular Papers (Long and Short) Deadline (SIGDial): April 2, 2021 (23:59 GMT-08)
- Notification for Regular Papers: TBA (as per SIGDial 2021)
- Camera-ready due (Regular Papers): TBA (as per SIGDial 2021)
- Late-breaking (LBR) and Work-In-Progress (WiP) abstracts Deadline: May 31, 2021
- Notification for LBR/WiP abstracts: July 5, 2021
- Event date: TBA (between July 29 - 31, 2021)

***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/
- For Late-breaking and Work-In-Progress abstracts please submit to safeconvai at macs.hw.ac.uk
- Please follow SIGDial 2021<http://www.colips.org/conferences/sigdial2021/wp/call-for-papers/> submission instructions and formatting guidelines.


***Organizers***
Gavin Abercrombie, Heriot-Watt University
Y-Lan Boureau, Facebook AI
Emily Dinan, Facebook AI
Saadia Gabriel, University of Washington
Alborz Geramifard, Facebook AI
Verena Rieser, Heriot-Watt University & ALANA AI
Yulia Tsvetkov, Carnegie Mellon University
Zeerak Waseem, University of Sheffield

***Senior advisory board***
Barbara Grosz, Harvard University
Pilar Manchón, Google
Ehud Reiter, University of Aberdeen
Jason Williams, Apple

***Contact:*** safeconvai at macs.hw.ac.uk
***Website:***https://sites.google.com/view/safety4convai/home
________________________________

Founded in 1821, Heriot-Watt is a leader in ideas and solutions. With campuses and students across the entire globe we span the world, delivering innovation and educational excellence in business, engineering, design and the physical, social and life sciences. This email is generated from the Heriot-Watt University Group, which includes:

  1.  Heriot-Watt University, a Scottish charity registered under number SC000278
  2.  Heriot- Watt Services Limited (Oriam), Scotland's national performance centre for sport. Heriot-Watt Services Limited is a private limited company registered is Scotland with registered number SC271030 and registered office at Research & Enterprise Services Heriot-Watt University, Riccarton, Edinburgh, EH14 4AS.

The contents (including any attachments) are confidential. If you are not the intended recipient of this e-mail, any disclosure, copying, distribution or use of its contents is strictly prohibited, and you should please notify the sender immediately and then delete it (including any attachments) from your system.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.uni-bielefeld.de/mailman2/unibi/public/iva-list/attachments/20210310/07efaaa6/attachment.html>