KIT | KIT-Bibliothek | Impressum | Datenschutz

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

Hoppe, Fabian ORCID iD icon; Dessı̀, Danilo; Sack, Harald


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.

Verlagsausgabe §
DOI: 10.5445/IR/1000139525
Veröffentlicht am 29.10.2021
Cover der Publikation
Zugehörige Institution(en) am KIT Institut für Angewandte Informatik und Formale Beschreibungsverfahren (AIFB)
Publikationstyp Proceedingsbeitrag
Publikationsjahr 2021
Sprache Englisch
Identifikator ISSN: 1613-0073
KITopen-ID: 1000139525
Erschienen in Proceedings of the Workshop on Deep Learning for Knowledge Graphs (DL4KG2020) co-located with the 17th Extended Semantic Web Conference 2020 (ESWC 2020), Heraklion, GR, June 2, 2020. Ed.: M. Alam
Veranstaltung Workshop on Deep Learning for Knowledge Graphs - 17th Extended Semantic Web Conference (DL4KG2020 - ESWC 2020), Online, 02.06.2020
Verlag RWTH Aachen
Serie CEUR Workshop Proceedings ; 2635
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page