Zero-shot cross-lingual transfer language selection using linguistic similarity

TL;DR

This paper investigates how linguistic similarity metrics can guide the selection of transfer languages in cross-lingual NLP tasks, improving performance over English-based transfer choices.

Contribution

It introduces a method using linguistic similarity to select optimal transfer languages, demonstrating improved transfer performance across multiple NLP tasks.

Findings

Linguistic similarity correlates with transfer performance.

Significant improvement over English as transfer source.

Method effective across diverse languages and tasks.

Abstract

We study the selection of transfer languages for different Natural Language Processing tasks, specifically sentiment analysis, named entity recognition and dependency parsing. In order to select an optimal transfer language, we propose to utilize different linguistic similarity metrics to measure the distance between languages and make the choice of transfer language based on this information instead of relying on intuition. We demonstrate that linguistic similarity correlates with cross-lingual transfer performance for all of the proposed tasks. We also show that there is a statistically significant difference in choosing the optimal language as the transfer source instead of English. This allows us to select a more suitable transfer language which can be used to better leverage knowledge from high-resource languages in order to improve the performance of language applications lacking data. For the study, we used datasets from eight different languages from three language families.