no code implementations • SIGDIAL (ACL) 2020 • Felix Gervits, Ravenna Thielstrom, Antonio Roque, Matthias Scheutz
Turn-entry timing is an important requirement for conversation, and one that spoken dialogue systems largely fail at.
no code implementations • ACL (NL4XAI, INLG) 2020 • Ravenna Thielstrom, Antonio Roque, Meia Chita-Tegmark, Matthias Scheutz
We then describe an evaluation that can be extended to further study the effects of varying the explanation templates.
no code implementations • 12 Oct 2021 • Felix Gervits, Gordon Briggs, Antonio Roque, Genki A. Kadomatsu, Dean Thurston, Matthias Scheutz, Matthew Marge
Dialogue agents that interact with humans in situated environments need to manage referential ambiguity across multiple modalities and ask for help as needed.
1 code implementation • SIGDIAL (ACL) 2021 • Felix Gervits, Antonio Roque, Gordon Briggs, Matthias Scheutz, Matthew Marge
Intelligent agents that are confronted with novel concepts in situated environments will need to ask their human teammates questions to learn about the physical world.
no code implementations • COLING 2020 • Vasanth Sarathy, Alexander Tsuetaki, Antonio Roque, Matthias Scheutz
We perform a corpus analysis to develop a representation of the knowledge and reasoning used to interpret indirect speech acts.
no code implementations • LREC 2020 • Antonio Roque, Alex Tsuetaki, er, Vasanth Sarathy, Matthias Scheutz
Resolving Indirect Speech Acts (ISAs), in which the intended meaning of an utterance is not identical to its literal meaning, is essential to enabling the participation of intelligent systems in peoples{'} everyday lives.
no code implementations • WS 2019 • Daniel Kasenberg, Antonio Roque, Ravenna Thielstrom, Meia Chita-Tegmark, Matthias Scheutz
We present an approach to generating natural language justifications of decisions derived from norm-based reasoning.
no code implementations • WS 2019 • Daniel Kasenberg, Antonio Roque, Ravenna Thielstrom, Matthias Scheutz
We present a set of capabilities allowing an agent planning with moral and social norms represented in temporal logic to respond to queries about its norms and behaviors in natural language, and for the human user to add and remove norms directly in natural language.