Back to the Roots

Predicting the Source Domain of Metaphors using Contrastive Learning

verfasst von
Meghdut Sengupta, Milad Alshomary, Henning Wachsmuth
Abstract

Metaphors frame a given target domain using concepts from another, usually more concrete, source domain. Previous research in NLP has focused on the identification of metaphors and the interpretation of their meaning. In contrast, this paper studies to what extent the source domain can be predicted computationally from a metaphorical text. Given a dataset with metaphorical texts from a finite set of source domains, we propose a contrastive learning approach that ranks source domains by their likelihood of being referred to in a metaphorical text. In experiments, it achieves reasonable performance even for rare source domains, clearly outperforming a classification baseline.

Organisationseinheit(en)
Fachgebiet Maschinelle Sprachverarbeitung
Institut für Künstliche Intelligenz
Typ
Aufsatz in Konferenzband
Seiten
137-142
Anzahl der Seiten
6
Publikationsdatum
2022
Publikationsstatus
Veröffentlicht
Peer-reviewed
Ja
ASJC Scopus Sachgebiete
Sprache und Linguistik, Artificial intelligence, Angewandte Informatik, Linguistik und Sprache
Ziele für nachhaltige Entwicklung
SDG 4 – Qualitativ hochwertige Bildung