MPI Colloquium Prof. Raquel Fernández

Conversational Common Ground in Referential Tasks: An Artificial Intelligence Perspective

Abstract

In collaborative dialogue, speakers build shared understanding by reusing expressions that proved to be effective for the task at hand. To investigate these processes, we collected a large-scale set of visually grounded, task-oriented dialogues in English designed to investigate common ground accumulating over a repeated referential task. I will present a series of experiments carried out on this dataset using tools from the fields of natural language processing and computer vision. Our results shed light into human referential communication and pave the way for building artificial conversational agents that are more human-like.

Short Biography

Raquel Fernández is Full Professor of Computational Linguistics and Dialogue Systems at the Institute for Logic, Language & Computation, University of Amsterdam, where she leads the Dialogue Modelling Group. Her work and interests revolve around language use in context, including computational semantics and pragmatics, dialogue interaction, visually-grounded language processing, and language learning, among others. Her group carries out research on these topics at the interface of computational linguistics, cognitive science and artificial intelligence.

Link to website

If you would like to meet with Raquel Fernández on February 21, 2023, please contact elli.tourtouri [at] mpi.nl (elli[dot]tourtouri[at]mpi[dot]nl)

Livestream link:  https://videoportal.mpi.nl/Mediasite/Play/b49e96b762194424b39e4b75bd62dad81d