Unified Pragmatic Models for Generating and Following Instructions
This work addresses the challenge of enhancing human-AI communication in sequential task environments, though it is incremental as it extends existing pragmatic models to sequential structures.
The paper tackled the problem of generating and following natural language instructions for complex sequential tasks by using explicit pragmatic inference, resulting in improved state-of-the-art performance for both listener and speaker models in diverse settings.
We show that explicit pragmatic inference aids in correctly generating and following natural language instructions for complex, sequential tasks. Our pragmatics-enabled models reason about why speakers produce certain instructions, and about how listeners will react upon hearing them. Like previous pragmatic models, we use learned base listener and speaker models to build a pragmatic speaker that uses the base listener to simulate the interpretation of candidate descriptions, and a pragmatic listener that reasons counterfactually about alternative descriptions. We extend these models to tasks with sequential structure. Evaluation of language generation and interpretation shows that pragmatic inference improves state-of-the-art listener models (at correctly interpreting human instructions) and speaker models (at producing instructions correctly interpreted by humans) in diverse settings.