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 | Dimensione | Formato | |
---|---|---|---|
paper8.pdf accesso aperto
Tipologia: versione editoriale
Dimensione 573.18 kB
Formato Adobe PDF
|
573.18 kB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.