Roman Kutlak

Demo: making plans scrutable with argumentation and natural language generation

Autonomous systems perform tasks without human guidance. Techniques for making autonomous systems scrutable and, hence, more transparent are required in order to support humans working with such systems. The Scrutable Autonomous Systems (SAsSy) demo shows a novel way of combining argumentation and natural language to generate a human understandable explanation dialogue. By interacting with SAsSy users are able to ask why a certain plan was selected for execution, why other alternatives were not selected, also allowing users to modify information in the system.

Production of Referring Expressions for an Unknown Audience: A Computational Model of Communal Common Ground.

This article presents a computational model of the production of referring expressions under uncertainty over the hearers knowledge. Although situations where the hearers knowledge is uncertain have seldom been addressed in the computational literature, they are common in ordinary communication, for example when a writer addresses an unknown audience, or when a speaker addresses a stranger. We propose a computational model composed of three complimentary heuristics based on, respectively, an estimation of the recipients knowledge, an estimation of the extent to which a property is unexpected, and the question of what is the optimum number of properties in a given situation. The model was tested in an experiment with human readers, in which it was compared against the Incremental Algorithm and human-produced descriptions. The results suggest that the new model outperforms the Incremental Algorithm in terms of the proportion of correctly identified entities and in terms of the perceived quality of the generated descriptions.