Introduction


Programme Schedule Announced -- Click here for the Program Schedule

Natural Conversation between humans and machines similar to conversations between two humans is considered a hallmark in intelligent systems. Conversational AI (Artificial Intelligence) is a key area of AI and it refers to technologies, such as chatbots or virtual agents, to which users can talk to as in by two humans.

Conversation systems need to be designed to work with people in a manner where humans can explain their needs and the systems can convince humans about making choices, and also comply with ethical standards in real life settings. It requires large volumes of data and techniques like machine learning and natural language processing to develop human like interactions.

The systems developed can take speech or text as input and process and output as text or speech in the language of the input or to a translated target language. Though this has been in research for the past many years, recently there is a renewed spurt of activity in chatbot development and research amongst the academia and the industry.


Most of the research and development done in this area are in English where the medium of conversation is in English language. There is very little work done in Indian languages and hardly any system developed where real time conversation is taking place.

Today conversational AI is not an interactive system but a transactional system at best. By transactional system we mean that the system is navigated through a set of instructions which are numerals instead of actual conversations. Effective and efficient techniques for human-machine conversations are still evolving.


Although, various machine learning methods are widely used for language understanding generation and entity detection, the wider problem of handling real time conversation is unaddressed. And the majority of the tools available are supporting rudimentary rule-based processing of conversations.


There is an urgent need to come up with methods, technologies, and evaluation metrics for chatbot/conversational systems research which uses an end-to-end conversation in Indian languages.
In this workshop we aim to bring together researchers working in the area of Conversational AI/chatbot developers, specifically addressing issues or providing solutions in Indian languages, which is the need of the hour.



Call For Papers


Papers are invited on substantial, original and unpublished research (also work in progress, authors must mention this in the paper) on all aspects of Conversational Artificial Intelligence, with a special focus on Indian languages.

We also welcome other languages which are less resourced and are not researched up on. (not English)

The areas of interest include, but are not limited to:

  • Analysis of Conversation and system Development
    • Chatbots for Citizen services, e-Governance
    • Dialog analysis and system development in any domain
    • Educational Chatbots, especially Distance Education
    • Design considerations of chatbots
    • Evaluation of metric for chatbot
    • Open domain chat systems
    • Novel Methods for NL Generation for conversations
    • Hybrid methods
    • Analysis of conversations
    • Conversation Corpora development and annotation conventions
  • Methods: Reasoning and Learning
    • Domain model acquisition, especially from unstructured text
    • Plan recognition in natural conversation
    • Planning and reasoning in the context of dialog systems
    • Handling uncertainty
    • Optimal dialog strategies
    • Learning to reason
    • Learning for dialog management
    • End2End models for conversation
  • Ethics, Privacy and Security
    • Ethical issues in log and data storage
    • Securing one’s chat

Submission Format


Long Papers

Long paper submissions must describe substantial, original, completed and unpublished work. Long papers may consist of up to 8 pages of content, plus unlimited references. Finalversions of long papers will be given one additional page of content (up to 9 pages) plus any no of pages for the references.


Short Papers

Short paper submissions must describe original and unpublished work. 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. Some kinds of short papers are:

  • A small, focused contribution
  • A negative result
  • An opinion piece
  • An interesting application nugget

Short papers may consist of up to 4 pages of content, plus unlimited references. Upon acceptance, short papers will be given 5 content pages in the proceedings. Authors are encouraged to use this additional page to address reviewers' comments in their final versions.


Instructions for Double-Blind Review

As reviewing will be double blind, papers must not include authors' names and affiliations. Furthermore, self-references or links (such as github) that reveal the author's identity, e.g., "We previously showed (Smith, 1991) .." must be avoided. Instead, use citations such as "Smith previously showed (Smith, 1991) ..." Papers that do not conform to these requirements will be rejected without review. Papers should not refer, for further detail, to documents that are not available to the reviewers. For example, do not omit or redact important citation information to preserve anonymity. Instead, use third person or named reference to this work, as described above ("Smith showed" rather than "we showed"). Papers may be accompanied by a resource (software and/or data) described in the paper, but these resources should be anonymized as well.



Paper Submission Templates

Submission is electronic, using the Softconf START conference management system. The submission site is now available at https://www.softconf.com/icon2021/ConvAI-IL-2021/

The deadline for submission of both long and short papers is November 15th, 2021 (GMT -12).

Both long and short papers must follow the ACL Author Guidelines
Style sheets (Latex, Word) are available here: https://acl2020.org/downloads/acl2020-templates.zip
The Overleaf template is also available here: https://www.overleaf.com/latex/templates/acl-2020-proceedings-template/zsrkcwjptpcd
Please do not modify these style files, or use templates designed for other conferences. Submissions that do not conform to the required styles, including paper size, margin width, and font size restrictions, will be rejected without review.


Workshop Organizers


Computational Linguistics Research Group (CLRG),
AU-KBC Research Centre



Sobha Lalitha Devi, AU-KBC Research Centre, Chennai, India.
Pattabhi RK Rao, AU-KBC Research Centre, Chennai, India.






Links