Cross-Domain Classification of Moral Values

1 code implementation • Findings (NAACL) 2022 • Enrico Liscio, Alin Dondera, Andrei Geadau, Catholijn Jonker, Pradeep Murukannaiah

However, domain-specific moral rhetoric poses challenges for transferring knowledge from one domain to another. We provide the first extensive investigation on the effects of cross-domain classification of moral values from text.

Classification domain classification

MAGMA: Manifold Regularization for MAEs

1 code implementation • 3 Dec 2024 • Alin Dondera, Anuj Singh, Hadi Jamali-Rad

Masked Autoencoders (MAEs) are an important divide in self-supervised learning (SSL) due to their independence from augmentation techniques for generating positive (and/or negative) pairs as in contrastive frameworks.