Understanding Class Representations: An Intrinsic Evaluation of Zero-Shot Text Classification

Loading...
Thumbnail Image
Date
2021
Volume
3404
Issue
Journal
Series Titel
Book Title
Publisher
Aachen, Germany : RWTH Aachen
Link to publishers version
Abstract

Frequently, Text Classification is limited by insufficient training data. This problem is addressed by Zero-Shot Classification through the inclusion of external class definitions and then exploiting the relations between classes seen during training and unseen classes (Zero-shot). However, it requires a class embedding space capable of accurately representing the semantic relatedness between classes. This work defines an intrinsic evaluation based on greater-than constraints to provide a better understanding of this relatedness. The results imply that textual embeddings are able to capture more semantics than Knowledge Graph embeddings, but combining both modalities yields the best performance.

Description
Keywords
Zero-Shot Learning, Text Classification, Class Representation, Embedding Model, Intrinsic Evaluation, Konferenzschrift
Citation
Hoppe, F., Dessì, D., & Sack, H. (2021). Understanding Class Representations: An Intrinsic Evaluation of Zero-Shot Text Classification (M. Alam, D. Buscaldi, M. Cochez, F. Osborne, D. Reforgiato Recupero, & H. Sack, eds.). Aachen, Germany : RWTH Aachen.
Collections
License
CC BY 4.0 Unported