让AI理解物体属性，用特征构建可解释的语义表示
Features-based embedding or Feature-grounding
- 用概念特征构建可解释的嵌入表示
- 实现共享表征与领域特征的对齐
- 适合需要可解释性的场景如医疗、自动驾驶
日常推理中，我们思考某个物体时会联想到其独特的属性，如重量、尺寸或密度、马力等抽象特征。这些预期由过往经验形成的类别知识塑造。本文研究如何在深度学习模型中重现这种基于知识的结构化思维，提出一种基于特征的嵌入方法，旨在建立可操作词典的共享表示与可解释的领域特定概念特征之间的对齐。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。