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.
@article{arxiv.2305.10349,
title = {Interactive Learning of Hierarchical Tasks from Dialog with GPT},
author = {Lane Lawley and Christopher J. MacLellan},
journal= {arXiv preprint arXiv:2305.10349},
year = {2023}
}