# Zero-shot Cross-lingual Transfer Learning with Multiple Source and Target Languages for Information Extraction: Language Selection and Adversarial Training

arXiv: https://arxiv.org/abs/2411.08785 · HTML: https://mlsanity.com/paper/2411.08785/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 3 of its 38 references that are in the map.
- First posted on arXiv 13 Nov 2024.

## Builds on (most cited first, 3 of 3)

- [Revisiting the Primacy of English in Zero-shot Cross-lingual Transfer](https://mlsanity.com/paper/2106.16171/) (2021)
- [Predicting the Performance of Multilingual NLP Models](https://mlsanity.com/paper/2110.08875/) (2021)
- [Analysing The Impact Of Linguistic Features On Cross-Lingual Transfer](https://mlsanity.com/paper/2105.05975/) (2021)

## Abstract (arXiv)

The majority of previous researches addressing multi-lingual IE are limited to zero-shot cross-lingual single-transfer (one-to-one) setting, with high-resource languages predominantly as source training data. As a result, these works provide little understanding and benefit for the realistic goal of developing a multi-lingual IE system that can generalize to as many languages as possible. Our study aims to fill this gap by providing a detailed analysis on Cross-Lingual Multi-Transferability (many-to-many transfer learning), for the recent IE corpora that cover a diverse set of languages. Specifically, we first determine the correlation between single-transfer performance and a wide range of linguistic-based distances. From the obtained insights, a combined language distance metric can be developed that is not only highly correlated but also robust across different tasks and model scales. Next, we investigate the more general zero-shot multi-lingual transfer settings where multiple languages are involved in the training and evaluation processes. Language clustering based on the newly defined distance can provide directions for achieving the optimal cost-performance trade-off in data (languages) selection problem. Finally, a relational-transfer setting is proposed to further incorporate multi-lingual unlabeled data based on adversarial training using the relation induced from the above linguistic distance.