Boosting Cross-Lingual Transfer via Self-Learning with Uncertainty Estimation

TL;DR

This paper introduces a self-learning approach with uncertainty estimation to improve cross-lingual transfer in multilingual models, significantly boosting performance on NER and NLI tasks across 40 languages.

Contribution

It proposes a novel self-learning framework utilizing uncertainty estimation to select high-quality pseudo-labels for better cross-lingual transfer.

Findings

Outperforms baselines by 10 F1 on NER

Achieves 2.5 higher accuracy on NLI

Effective across 40 languages

Abstract

Recent multilingual pre-trained language models have achieved remarkable zero-shot performance, where the model is only finetuned on one source language and directly evaluated on target languages. In this work, we propose a self-learning framework that further utilizes unlabeled data of target languages, combined with uncertainty estimation in the process to select high-quality silver labels. Three different uncertainties are adapted and analyzed specifically for the cross lingual transfer: Language Heteroscedastic/Homoscedastic Uncertainty (LEU/LOU), Evidential Uncertainty (EVI). We evaluate our framework with uncertainties on two cross-lingual tasks including Named Entity Recognition (NER) and Natural Language Inference (NLI) covering 40 languages in total, which outperforms the baselines significantly by 10 F1 on average for NER and 2.5 accuracy score for NLI.