Improving zero-shot learning baselines with commonsense knowledge

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...

Full description

Saved in:
Bibliographic Details
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:
Online Access:https://hdl.handle.net/10356/170538
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
Description
Summary: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 to facilitate this transfer by improving the association between visual and semantic embeddings. In this paper, we take advantage of explicit relations between nodes defined in ConceptNet, a commonsense knowledge graph, to generate commonsense embeddings of the class labels by using a graph convolution network-based autoencoder. Our experiments performed on three standard benchmark datasets surpass the strong baselines when we fuse our commonsense embeddings with existing semantic embeddings, i.e., human-defined attributes and distributed word embeddings. This work paves the path to more brain-inspired approaches to zero-short learning.