ESA Virtual Assistant in ESASky: enabling archival data exploration via natural language processing

ESASky (sky.esa.int) is a powerful visualisation tool developed by the Data Science and Archives Division at ESAC that can be used to discover multi-mission, multi-wavelength and multi-messenger astronomical data anywhere on the sky in a very intuitive way. Since its inception ESASky has been at the forefront of archival data exploration and an increasing number of astronomers are using ESASky to do their science. In parallel, a wide variety of AI technologies have become available in recent years that will enable new ways to interact with astronomical data centres. In this context, we would like to show how the ESA Virtual Assistant (EVA) has been integrated in ESASky and how it allows users to explore its data contents using natural language processing. In practice what this means is that users can interact with EVA using simple sentences that trigger the commanding of ESASky via its API. At the moment the virtual assistant has been programmed with a sufficient number of interactions to carry out most of the tasks that a typical user would do in the ESASky web interface with the mouse. However, exposing the virtual assistant to a larger audience will allow us to train the neural network running behind the virtual assistant to understand more complex sentences and commands, opening new avenues for more advanced exploration of ESASky.