Decoding Communications with Partial Information

TL;DR

This paper investigates decoding communication under partial observability, proposing a learning algorithm to infer hidden information for language acquisition in more realistic, less observable environments.

Contribution

It introduces a formal framework for partial information decoding in language learning and presents a novel learning algorithm to address this challenge.

Findings

Demonstrates solutions in toy environments

Identifies challenges in general settings

Proposes a learning-based decoding algorithm

Abstract

Machine language acquisition is often presented as a problem of imitation learning: there exists a community of language users from which a learner observes speech acts and attempts to decode the mappings between utterances and situations. However, an interesting consideration that is typically unaddressed is partial observability, i.e. the learner is assumed to see all relevant information. This paper explores relaxing this assumption, thereby posing a more challenging setting where such information needs to be inferred from knowledge of the environment, the actions taken, and messages sent. We see several motivating examples of this problem, demonstrate how they can be solved in a toy setting, and formally explore challenges that arise in more general settings. A learning-based algorithm is then presented to perform the decoding of private information to facilitate language acquisition.