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

TL;DR

This paper demonstrates that multi-lingual sentence embeddings enable transfer of predictive models for legal decision segmentation across different languages, jurisdictions, and legal domains, improving robustness and performance.

Contribution

It introduces a transfer learning approach using language-agnostic sentence representations for legal text analysis across diverse legal systems and languages.

Findings

Models generalize across different legal contexts and languages.

Training on multiple contexts enhances robustness and accuracy.

Pooling data from various contexts improves in-context performance.

Abstract

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 Language-Agnostic 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.