Developers around the world are striving to build software that leverages conversational AI. It is helpful to split these efforts to 5 levels of capability, in analogy with research on autonomous vehicles. There is no straightforward dichotomy between dumb chatbots and AGI, but a series of gradations which can help us understand progress. I will talk about the key characteristics of level 3 conversational AI, which is where the most advanced teams are today. I will discuss the difficult machine learning and engineering problems that this poses, and how we see solutions developing within the Rasa community, leveraging research in the field to advance the state of the art.
About the speaker: Dr. Alan Nichol is the co-founder and CTO of Rasa, and a maintainer of Rasa NLU and Rasa Core, the leading open source libraries for building conversational AI. He is also the author of the DataCamp course “building chatbots in python”. He holds a PhD in machine learning from the University of Cambridge and has years of experience building AI products in industry.
Bots (short for software robots) are software applications that perform often repetitive or simple tasks. In particular, social and chat bots interacting with humans are a recent research topic. Similarly, bots can be used to automate many tasks that are performed by software practitioners and teams in their day-to-day work. Recent work argue that bots can save developers' time and significantly increase productivity. Therefore, the goal of this one-day workshop is to bring together software engineering researchers and practitioners to discuss the opportunities and challenges of bots in software engineering. We solicit 4 page, research, experience report and position papers. Research papers are expected to describe new research results and make contributions to the body knowledge in the area. Experience reports are expected to describe experiences with (amongst other things) the development, deployment, and maintenance of bot-based systems in the software engineering domain. Position papers are expected to discuss controversial issues in the field, or describe interesting or thought provoking ideas that are not yet fully developed. Papers will be reviewed by at least three program committee members. Accepted research and experience report papers will be invited to give a talk to present their findings. Authors of accepted position papers will be invited to give a short lightning talk. Papers may address issues along the general themes, including but not limited, to the following topics:
Submission must not exceed 4 pages, including all text, figures, tables, and appendices; one additional page containing only references is permitted. Submissions must conform to the IEEE Conference Proceedings Formatting Guidelines (title in 24pt font and full text in 10pt type, LaTEX users must use \documentclass[10pt,conference]{IEEEtran} without including the compsoc or compsocconf option).
The submission must also comply with the ACM plagiarism policy and procedures. In particular, submissions must not have been published elsewhere and must not be under review elsewhere. The submission must also comply with the IEEE Policy on Authorship.
Submissions to the workshop can be made via easychair by the submission deadline.
If a submission is accepted, at least one author of the paper is required to attend the workshop and present the paper in person. All accepted workshop papers will be published in the proceedings by IEEE CS.