Learning in the Rational Speech Acts Model

TL;DR

This paper enhances the Rational Speech Acts model by integrating learned classifiers as hidden layers, enabling data-driven learning and expanding its applicability to natural language processing tasks.

Contribution

It introduces a method to train RSA models with learned classifiers, allowing automatic lexical knowledge acquisition from data, and demonstrates improved performance on language generation tasks.

Findings

Improved referential expression generation performance

Incorporation of linguistic features enhances RSA effectiveness

Model enables learning from data in pragmatic language modeling

Abstract

The Rational Speech Acts (RSA) model treats language use as a recursive process in which probabilistic speaker and listener agents reason about each other's intentions to enrich the literal semantics of their language along broadly Gricean lines. RSA has been shown to capture many kinds of conversational implicature, but it has been criticized as an unrealistic model of speakers, and it has so far required the manual specification of a semantic lexicon, preventing its use in natural language processing applications that learn lexical knowledge from data. We address these concerns by showing how to define and optimize a trained statistical classifier that uses the intermediate agents of RSA as hidden layers of representation forming a non-linear activation function. This treatment opens up new application domains and new possibilities for learning effectively from data. We validate the model on a referential expression generation task, showing that the best performance is achieved by incorporating features approximating well-established insights about natural language generation into RSA.