Learning to refer informatively by amortizing pragmatic reasoning
This work addresses the challenge of computational efficiency in pragmatic language generation for AI systems, offering an incremental improvement over existing methods.
The paper tackled the problem of generating informative language efficiently by amortizing pragmatic reasoning, showing that their model quickly produces effective and concise language across contexts without explicit reasoning, achieving strong performance on communication game datasets.
A hallmark of human language is the ability to effectively and efficiently convey contextually relevant information. One theory for how humans reason about language is presented in the Rational Speech Acts (RSA) framework, which captures pragmatic phenomena via a process of recursive social reasoning (Goodman & Frank, 2016). However, RSA represents ideal reasoning in an unconstrained setting. We explore the idea that speakers might learn to amortize the cost of RSA computation over time by directly optimizing for successful communication with an internal listener model. In simulations with grounded neural speakers and listeners across two communication game datasets representing synthetic and human-generated data, we find that our amortized model is able to quickly generate language that is effective and concise across a range of contexts, without the need for explicit pragmatic reasoning.