Interactive Learning of Hierarchical Tasks from Dialog with GPT

TL;DR

This paper introduces an interactive system that uses GPT to learn and represent hierarchical tasks from dialog, enabling natural, flexible, and interpretable task acquisition and reuse.

Contribution

It presents a novel GPT-based approach for hierarchical task learning from dialog, improving linguistic robustness over traditional parsing methods.

Findings

System tolerates diverse linguistic expressions

Hierarchical task representations enable reuse

Effective in natural conversational settings

Abstract

We present a system for interpretable, symbolic, interactive task learning from dialog using a GPT model as a conversational front-end. The learned tasks are represented as hierarchical decompositions of predicate-argument structures with scoped variable arguments. By using a GPT model to convert interactive dialog into a semantic representation, and then recursively asking for definitions of unknown steps, we show that hierarchical task knowledge can be acquired and re-used in a natural and unrestrained conversational environment. We compare our system to a similar architecture using a more conventional parser and show that our system tolerates a much wider variety of linguistic variance.