# Massively Multilingual Transfer for NER

## TL;DR

This paper introduces techniques for improving cross-lingual transfer in NER using a massive set of source models, significantly enhancing performance in low-resource languages.

## Contribution

It proposes two novel transfer modulation techniques for zero-shot and few-shot learning in a massively multilingual setting, outperforming standard baselines.

## Key findings

- Our methods outperform strong baselines in NER transfer tasks.
- Unsupervised transfer modulation rivals oracle model selection.
- Techniques are effective in low-resource and distant language scenarios.

## Abstract

In cross-lingual transfer, NLP models over one or more source languages are applied to a low-resource target language. While most prior work has used a single source model or a few carefully selected models, here we consider a `massive' setting with many such models. This setting raises the problem of poor transfer, particularly from distant languages. We propose two techniques for modulating the transfer, suitable for zero-shot or few-shot learning, respectively. Evaluating on named entity recognition, we show that our techniques are much more effective than strong baselines, including standard ensembling, and our unsupervised method rivals oracle selection of the single best individual model.