Features-based embedding or Feature-grounding
This addresses the challenge of incorporating prior knowledge and conceptual categories into AI models for improved reasoning, though it appears incremental as it builds on existing embedding methods.
The paper tackles the problem of reproducing knowledge-based structured thinking in deep learning models by introducing a feature-grounded embedding approach to align shareable representations with interpretable domain-specific conceptual features, but no concrete results or numbers are provided.
In everyday reasoning, when we think about a particular object, we associate it with a unique set of expected properties such as weight, size, or more abstract attributes like density or horsepower. These expectations are shaped by our prior knowledge and the conceptual categories we have formed through experience. This paper investigates how such knowledge-based structured thinking can be reproduced in deep learning models using features based embeddings. Specially, it introduces an specific approach to build feature-grounded embedding, aiming to align shareable representations of operable dictionary with interpretable domain-specific conceptual features.