Stage-oe-small.jpg

Inproceedings3920

Aus Aifbportal
Wechseln zu:Navigation, Suche


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


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



Published: 2021 Oktober

Buchtitel: Proceedings of DL4KG workshop, co-located with the 20th International Semantic Web Conference (ISWC 2021)
Verlag: CEUR Workshop Proceedings

Nicht-referierte Veröffentlichung

BibTeX

Kurzfassung
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.

Download: Media:Understanding Class Representations An Intrinsic Evaluation of Zero-Shot Text Classification_HOPPE_DL4KG∂ISWC2021 pdf



Forschungsgruppe

Information Service Engineering


Forschungsgebiet