Revisiting Projection-based Data Transfer for Cross-Lingual Named Entity Recognition in Low-Resource Languages

TL;DR

This paper improves cross-lingual NER for low-resource languages by refining annotation projection with back-translation and a novel matching approach, outperforming existing methods across multiple datasets.

Contribution

It introduces two enhancements to projection-based cross-lingual NER, demonstrating superior performance over existing methods in low-resource scenarios.

Findings

Refined word alignments via back-translation improve accuracy.

A novel projection matching approach enhances entity transfer.

Outperforms existing projection-based methods on 57-language datasets.

Abstract

Cross-lingual Named Entity Recognition (NER) leverages knowledge transfer between languages to identify and classify named entities, making it particularly useful for low-resource languages. We show that the data-based cross-lingual transfer method is an effective technique for crosslingual NER and can outperform multilingual language models for low-resource languages. This paper introduces two key enhancements to the annotation projection step in cross-lingual NER for low-resource languages. First, we explore refining word alignments using back-translation to improve accuracy. Second, we present a novel formalized projection approach of matching source entities with extracted target candidates. Through extensive experiments on two datasets spanning 57 languages, we demonstrated that our approach surpasses existing projectionbased methods in low-resource settings. These findings highlight the robustness of projection-based data transfer as an alternative to model-based methods for crosslingual named entity recognition in lowresource languages.