Improving zero-shot learning baselines with commonsense knowledge

• Main Authors: Roy, Abhinaba, Ghosal, Deepanway, Cambria, Erik, Majumder, Navonil, Mihalcea, Rada, Poria, Soujanya
• Other Authors: School of Computer Science and Engineering
• Format: Article
• Language: English
• Published: 2023
• Subjects: Engineering::Computer science and engineering; Commonsense Knowledge; Zero-shot Learning
• Online Access: https://hdl.handle.net/10356/170538
• Institution: Nanyang Technological University

Zero-shot learning — the problem of training and testing on a completely disjoint set of classes — relies greatly on its ability to transfer knowledge from train classes to test classes. Traditionally semantic embeddings consisting of human-defined attributes or distributed word embeddings are used...