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

arXiv: https://arxiv.org/abs/2112.07882 · HTML: https://mlsanity.com/paper/2112.07882/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 42 references that are in the map.
- First posted on arXiv 15 Dec 2021.

## Builds on (most cited first, 12 of 12)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyond](https://mlsanity.com/paper/1812.10464/) (2018)
- [MLQA: Evaluating Cross-lingual Extractive Question Answering](https://mlsanity.com/paper/1910.07475/) (2019)
- [Massively Multilingual Neural Machine Translation](https://mlsanity.com/paper/1903.00089/) (2019)
- [Deep Learning Models for Multilingual Hate Speech Detection](https://mlsanity.com/paper/2004.06465/) (2020)
- [Identification of Rhetorical Roles of Sentences in Indian Legal Judgments](https://mlsanity.com/paper/1911.05405/) (2019)
- [Computer-Assisted Creation of Boolean Search Rules for Text Classification in the Legal Domain](https://mlsanity.com/paper/2112.05807/) (2021)
- [Bridging the domain gap in cross-lingual document classification](https://mlsanity.com/paper/1909.07009/) (2019)
- [Performance in the Courtroom: Automated Processing and Visualization of Appeal Court Decisions in France](https://mlsanity.com/paper/2006.06251/) (2020)

## Built on by (most cited first, 11 of 11)

- [Unlocking Practical Applications in Legal Domain: Evaluation of GPT for Zero-Shot Semantic Annotation of Legal Texts](https://mlsanity.com/paper/2305.04417/) (2023)
- [Bringing order into the realm of Transformer-based language models for artificial intelligence and law](https://mlsanity.com/paper/2308.05502/) (2023)
- [Extractive Summarization of Legal Decisions using Multi-task Learning and Maximal Marginal Relevance](https://mlsanity.com/paper/2210.12437/) (2022)
- [MultiLegalSBD: A Multilingual Legal Sentence Boundary Detection Dataset](https://mlsanity.com/paper/2305.01211/) (2023)
- [EUROPA: A Legal Multilingual Keyphrase Generation Dataset](https://mlsanity.com/paper/2403.00252/) (2024)
- [Mind Your Neighbours: Leveraging Analogous Instances for Rhetorical Role Labeling for Legal Documents](https://mlsanity.com/paper/2404.01344/) (2024)
- [Using LLMs to Discover Legal Factors](https://mlsanity.com/paper/2410.07504/) (2024)
- [Data-Centric Machine Learning in the Legal Domain](https://mlsanity.com/paper/2201.06653/) (2022)
- [Toward an Intelligent Tutoring System for Argument Mining in Legal Texts](https://mlsanity.com/paper/2210.13635/) (2022)
- [Mining Legal Arguments to Study Judicial Formalism](https://mlsanity.com/paper/2512.11374/) (2025)
- [Are manual annotations necessary for statutory interpretations retrieval?](https://mlsanity.com/paper/2506.13965/) (2025)

## Abstract (arXiv)

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.