Learning in the Rational Speech Acts Model
This work improves the RSA model for computational linguistics applications, making it more practical for natural language processing tasks by enabling data-driven learning, though it is incremental in nature.
The paper addresses the Rational Speech Acts (RSA) model's limitations by developing a trained statistical classifier that integrates RSA agents as hidden layers, enabling learning from data without manual lexicon specification. It validates this approach on a referential expression generation task, achieving best performance by incorporating features from natural language generation insights.
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.