Lex Rosetta: Transfer of Predictive Models Across Languages, Jurisdictions, and Legal Domains

Investor logo

Warning

This publication doesn't include Institute of Computer Science. It includes Faculty of Law. Official publication website can be found on muni.cz.
Authors

ŠAVELKA Jaromír WESTERMANN Hannes BENYEKHLEF Karim ALEXANDER Charlotte S. GRANT Jayla C. AMARILES Restrepo David HAMDANI Rajaa El MEEUS Sébastien TROUSSEL Aurore ARASZKIEWICZ Michal ASHLEY Kevin D. ASHLEY Alexandra BRANTING Karl FALDUTI Mattia GRABMAIR Matthias HARAŠTA Jakub NOVOTNÁ Tereza TIPPETT Elizabeth JOHNSON Shiwanni

Year of publication 2021
Type Article in Proceedings
Conference Eighteenth International Conference on Artificial Intelligence and Law: Proceedings of the Conference
MU Faculty or unit

Faculty of Law

Citation
Web
Doi http://dx.doi.org/10.1145/3462757.3466149
Keywords multi-lingual sentence embeddings; transfer learning; domain adaptation; adjudicatory decisions; document segmentation; annotation
Attached files
Description In this paper, we examine the use of multi-lingual sentence embeddings to transfer predictive models for functional segmentation of adjudicatory decisions across jurisdictions, legal systems (common and civil law), languages, and domains (i.e. contexts). Mechanisms for utilizing linguistic resources outside of their original context have significant potential benefits in AI & Law because differences between legal systems, languages, or traditions often block wider adoption of research outcomes. We analyze the use of LanguageAgnostic Sentence Representations in sequence labeling models using Gated Recurrent Units (GRUs) that are transferable across languages. To investigate transfer between different contexts we developed an annotation scheme for functional segmentation of adjudicatory decisions. We found that models generalize beyond the contexts on which they were trained (e.g., a model trained on administrative decisions from the US can be applied to criminal law decisions from Italy). Further, we found that training the models on multiple contexts increases robustness and improves overall performance when evaluating on previously unseen contexts. Finally, we found that pooling the training data from all the contexts enhances the models’ in-context performance.
Related projects:

You are running an old browser version. We recommend updating your browser to its latest version.

More info