Cross-Lingual NER Transfer Degradation Under Source-Target Label Distribution Divergence in Low-Resource Settings

Multilingual Language Models (MLLMs) exhibit robust cross-lingual transfer capabilities, or the ability to leverage information acquired in a source language and apply it to a target language. These capabilities find practical applications in well-established Natural Language Processing (NLP) tasks such as Named Entity Recognition (NER). This study aims to investigate the effectiveness of a source language when applied to a target language, particularly in the context of perturbing the input test set. We evaluate on 13 pairs of languages, each including one high-resource language (HRL) and one Research goal: How does the performance of cross-lingual NER transfer degrade when the source language label distribution diverges significantly from the target language in low-resource settings? Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.2/10. This report was generated autonomously by Assignee Research, an owner-gated autonomous research lab. The content synthesizes findings from peer-reviewed papers. Tribunal score: 8.2/10.