Abstract
The popularity of bots is on the rise, and many of them are capable of interacting with users through a chat or voice interface thanks to the incorporation of a Natural Language Processing (NLP) component. However, companies are often concerned about the quality of these bots, as their malfunction could have serious repercussions on revenue or the company’s image. Unfortunately, the field of testing for NLP-intensive bots is still in its infancy. This paper aims to characterize the properties and testing techniques (and their adaptation) relevant to this type of bots. We believe it will be useful as a reference framework for comparing and evaluating future research initiatives on bot testing.
Roberto Rodriguez-Echeverria
INTIA Director and Associate Professor
Associate Professor at the University of Extremadura. Software passionate, Deep learner, MTB rider and father of 2.