Timezone: »
Models of context-sensitive communication often use the Rational Speech Act framework (RSA; Frank & Goodman, 2012), which formulates listeners and speakers in a cooperative reasoning process. Large-scale applications of RSA have relied on training models to imitate human behaviors using contextually grounded datasets, but collecting such data can be costly. Here, we propose a new approach to scalable pragmatics, building upon recent theoretical results (Zaslavsky et al., 2020) that characterize pragmatic reasoning in terms of general information-theoretic principles. Specifically, we propose an architecture and learning process in which agents acquire pragmatic policies via self-supervision instead of imitating human data. This work suggests a new principled approach for equipping artificial agents with pragmatic skills via self-supervision, which is grounded both in pragmatic theory and in information theory.
Author Information
Jennifer Hu (Massachusetts Institute of Technology)
Roger Levy (Massachusetts Institute of Technology)
Noga Zaslavsky (MIT)
More from the Same Authors
-
2021 Workshop: Meaning in Context: Pragmatic Communication in Humans and Machines »
Jennifer Hu · Noga Zaslavsky · Aida Nematzadeh · Michael Franke · Roger Levy · Noah Goodman -
2021 : Opening remarks »
Jennifer Hu · Noga Zaslavsky · Aida Nematzadeh · Michael Franke · Roger Levy · Noah Goodman -
2021 Poster: Grammar-Based Grounded Lexicon Learning »
Jiayuan Mao · Freda Shi · Jiajun Wu · Roger Levy · Josh Tenenbaum -
2019 : Panel Discussion »
Jacob Andreas · Edward Gibson · Stefan Lee · Noga Zaslavsky · Jason Eisner · Jürgen Schmidhuber -
2019 : Invited Talk - 2 »
Noga Zaslavsky -
2017 : Efficient human-like semantic representations via the information bottleneck principle »
Noga Zaslavsky