Analogical Q/A Training

When people learn to operate in new domains, they do not start learning language from scratch. They reuse general-purpose language knowledge and skills, and rapidly adapt to new domains. Analogical Q/A training enables general-purpose semantic parsers to be rapidly adapted to new tasks and domains, with high data-efficiency. Moreover, it can use semantics tied to a broad ontology to self-annotate, thereby reducing the training work considerably. The AQA approach analyzes questions and answers (with answers either annotated or self-annotated) and produces query cases that are retrieved and used via analogical matching to construct queries.

Analogical Q/A Training Big Picture

To demonstrate data efficiency, consider training on just these two examples from the classic Geoquery domain:

Given just these two training examples, a Companion using AQA training can now answer

as well as any other question that can be understood as a composition of the query cases it has learned thus far. Traditional machine learning systems typically need around 600 training examples to learn a semantic parser for Geoquery. The explainability of analogical learning enables the construction of optimal training sequences, so we can explore what the minimum number of examples might be. It turns out that 50 examples suffice to achieve comparable performance.

Analogical Q/A Training learning curve on Geoquery

Analogical Q/A training has been used with several other datasets, and is used in the Computer Science Department Kiosk, a deployed Companion-based system which provides information about the department to visitors.

Selected Relevant Papers

Relevant Projects

Towards Intelligent Agents that Learn by Multimodal Communication

| Back to Ideas page | Back to QRG Home Page