KR2020Proceedings of the 17th International Conference on Principles of Knowledge Representation and ReasoningProceedings of the 17th International Conference on Principles of Knowledge Representation and Reasoning

Rhodes, Greece. September 12-18, 2020.

Edited by
  1. Diego Calvanese
  2. Esra Erdem
  3. Michael Thielscher

ISSN: 2334-1033
ISBN: 978-0-9992411-7-2

Sponsored by
Published by

Copyright © 2020 International Joint Conferences on Artificial Intelligence Organization

Ontology-guided Semantic Composition for Zero-shot Learning

  1. Jiaoyan Chen(Department of Computer Science, University of Oxford, UK)
  2. Freddy Lécué(INRIA, France, CortAIx@Thales, Canada)
  3. Yuxia Geng(College of Computer Science, Zhejiang University, China)
  4. Jeff Z. Pan(School of Informatics, The University of Edinburgh, UK, Department of Computer Science, The University of Aberdeen, UK)
  5. Huajun Chen(College of Computer Science, Zhejiang University, China)
PDF
BibTeX
DOI 10.24963/kr.2020/87

Keywords

  1. Transfer learning-
  2. Reasoning and learning over knowledge graphs-
  3. Neural-symbolic learning-General
  4. Logic-based learning algorithms-General

Abstract

Zero-shot learning (ZSL) is a popular research problem that aims at predicting for those classes that have never appeared in the training stage by utilizing the inter-class relationship with some side information. In this study, we propose to model the compositional and expressive semantics of class labels by an OWL (Web Ontology Language) ontology, and further develop a new ZSL framework with ontology embedding. The effectiveness has been verified by some primary experiments on animal image classification and visual question answering.