The research area of human–robot interaction has the goal to develop robotic agents that exhibit socially intelligent behaviour while interacting with human partners. Despite the clear relationship between social intelligence and fluent, flexible linguistic interaction, in practice few interactive robots employ anything beyond a simple template-based process when generating output. Developers of robot systems often do not take advantage of the flexibility afforded by natural language generation when generating output in interactive settings and dynamic environments or when output must be generated in different contexts or multiple target languages.
In similar fashion, interactive settings and dynamic environments open up interesting research problems in generation, which have not received much attention in the natural language generation community, yet. HRI researchers will bring these challenges to the workshop and with them their expertise on dynamic, uncertain representations of context, real-time planning, and computational perspectives on studying and modelling interaction.
The workshop on NLG for HRI will bring these two research communities together and aims to provide opportunities for interdisciplinary dialogue between researchers, to spread knowledge on methods, resources, best practice and solutions, as well as to foster cooperation on interesting research problems.
The workshop will also be of potential interest to researchers from other fields that focus on ‘interaction’ such as spoken dialogue systems, intelligent virtual agents, or intelligent user interfaces.
To ensure that all participants have a common starting ground, we will begin with short tutorial-style introductions to both of the fields involved. We will then invite participants to give short talks about their research, based on the issues and challenges identified in their position papers. For the final session of the workshop, we will encourage open discussion and collaboration among the participants, using an ‘unconference’ format such as Open Space.
We will aim to produce a journal paper after the workshop in order to reach wider audiences by emphasising the open challenges, issues, and the possible solutions for NLG for HRI. The position-paper authors and other participants will be invited to co-author the journal paper in the months following the workshop.