Interactive Learning of Hierarchical Tasks from Dialog with GPT
This work addresses the challenge of interpretable and interactive task learning for AI systems, though it appears incremental as it builds on existing dialog and parsing methods.
The paper tackles the problem of acquiring hierarchical task knowledge from natural dialog by using GPT as a conversational front-end to convert dialog into symbolic representations, resulting in a system that tolerates more linguistic variance compared to a conventional parser-based approach.
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.