Scalable pragmatic communication via self-supervision
Abstract
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. However, the standard RSA formulation can only be applied to small domains, and large-scale applications have relied on imitating human behavior. 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.
- Publication:
-
arXiv e-prints
- Pub Date:
- August 2021
- DOI:
- 10.48550/arXiv.2108.05799
- arXiv:
- arXiv:2108.05799
- Bibcode:
- 2021arXiv210805799H
- Keywords:
-
- Computer Science - Computation and Language;
- Computer Science - Artificial Intelligence
- E-Print:
- Workshop on Self-Supervised Learning @ ICML 2021