Cross-Domain Generalization and Knowledge Transfer in Transformers Trained on Legal Data

Jaromír Šavelka; Hannes Westermann; Karim Benyekhlef

doi:10.48550/arXiv.2112.07870

Cross-Domain Generalization and Knowledge Transfer in Transformers Trained on Legal Data

AUTHORS> Jaromír Šavelka; Hannes Westermann; Karim Benyekhlef

2021 · arXiv

Read at the source ↗DOI 10.48550/arXiv.2112.07870

ABSTRACT

We analyze the ability of pre-trained language models to transfer knowledge among datasets annotated with different type systems and to generalize beyond the domain and … Read the full abstract at the source

AUTHOR KEYWORDS> Transfer learning; transformers; cross-domain generalization; case-law, rhetorical roles, document classification

VERIFICATION

Publication record checked · 2026-10-07