# Realistic Zero-Shot Cross-Lingual Transfer in Legal Topic Classification

arXiv: https://arxiv.org/abs/2206.03785 · HTML: https://mlsanity.com/paper/2206.03785/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 4 references that are in the map.
- First posted on arXiv 8 Jun 2022.

## Builds on (most cited first, 2 of 2)

- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [UNKs Everywhere: Adapting Multilingual Language Models to New Scripts](https://mlsanity.com/paper/2012.15562/) (2020)

## Built on by (most cited first, 4 of 4)

- [An Empirical Study on Cross-X Transfer for Legal Judgment Prediction](https://mlsanity.com/paper/2209.12325/) (2022)
- [Comparison between parameter-efficient techniques and full fine-tuning: A case study on multilingual news article classification](https://mlsanity.com/paper/2308.07282/) (2023)
- [SheffieldVeraAI at SemEval-2023 Task 3: Mono and multilingual approaches for news genre, topic and persuasion technique classification](https://mlsanity.com/paper/2303.09421/) (2023)
- [Legal-Tech Open Diaries: Lesson learned on how to develop and deploy light-weight models in the era of humongous Language Models](https://mlsanity.com/paper/2210.13086/) (2022)

## Abstract (arXiv)

We consider zero-shot cross-lingual transfer in legal topic classification using the recent MultiEURLEX dataset. Since the original dataset contains parallel documents, which is unrealistic for zero-shot cross-lingual transfer, we develop a new version of the dataset without parallel documents. We use it to show that translation-based methods vastly outperform cross-lingual fine-tuning of multilingually pre-trained models, the best previous zero-shot transfer method for MultiEURLEX. We also develop a bilingual teacher-student zero-shot transfer approach, which exploits additional unlabeled documents of the target language and performs better than a model fine-tuned directly on labeled target language documents.