Understanding class representations: An intrinsic evaluation of zero-shot text classification
Dessi Danilo.;
2021-01-01
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.File | Size | Format | |
---|---|---|---|
paper8.pdf open access
Type: versione editoriale
Size 573.18 kB
Format Adobe PDF
|
573.18 kB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.