A Computational Interface to Translate Strategic Intent from Unstructured Language in a Low-Data Setting

TL;DR

This paper introduces a computational interface that translates unstructured language describing strategic intent into actionable goals and constraints, enabling autonomous systems to understand high-level human commands in low-data environments.

Contribution

The authors develop a novel model trained on a new dataset that outperforms human interpreters and ChatGPT in inferring strategic intent from language in low-data settings.

Findings

Model significantly outperforms human interpreters (p < 0.05).

Model outperforms ChatGPT in low-data scenarios (p < 0.05).

Collected dataset of over 1000 language-strategy examples.

Abstract

Many real-world tasks involve a mixed-initiative setup, wherein humans and AI systems collaboratively perform a task. While significant work has been conducted towards enabling humans to specify, through language, exactly how an agent should complete a task (i.e., low-level specification), prior work lacks on interpreting the high-level strategic intent of the human commanders. Parsing strategic intent from language will allow autonomous systems to independently operate according to the user's plan without frequent guidance or instruction. In this paper, we build a computational interface capable of translating unstructured language strategies into actionable intent in the form of goals and constraints. Leveraging a game environment, we collect a dataset of over 1000 examples, mapping language strategies to the corresponding goals and constraints, and show that our model, trained on this dataset, significantly outperforms human interpreters in inferring strategic intent (i.e., goals and constraints) from language (p < 0.05). Furthermore, we show that our model (125M parameters) significantly outperforms ChatGPT for this task (p < 0.05) in a low-data setting.