CLOct 8, 2020

Generating Instructions at Different Levels of Abstraction

arXiv:2010.03982v1991 citations
Originality Incremental advance
AI Analysis

This addresses the problem of customizing instruction generation for novice and expert users, but it is incremental as it applies hierarchical planning to a specific domain.

The paper tackled generating technical instructions at varying abstraction levels for different user expertise, showing in Minecraft that a balanced abstraction strategy outperforms others in user evaluations.

When generating technical instructions, it is often convenient to describe complex objects in the world at different levels of abstraction. A novice user might need an object explained piece by piece, while for an expert, talking about the complex object (e.g. a wall or railing) directly may be more succinct and efficient. We show how to generate building instructions at different levels of abstraction in Minecraft. We introduce the use of hierarchical planning to this end, a method from AI planning which can capture the structure of complex objects neatly. A crowdsourcing evaluation shows that the choice of abstraction level matters to users, and that an abstraction strategy which balances low-level and high-level object descriptions compares favorably to ones which don't.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes