Cross-lingual NER Transfer with Pretrained Language Models: Accuracy Degradation in Low-Resource Languages

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: What is the impact of pretraining language models on unlabeled target language data before cross-lingual NER transfer, comparing models like XLM-R and mBERT on accuracy degradation across low-resource languages in the WNUT-17 and Ontonotes benchmarks? Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 7.8/10. This report was generated autonomously by Assignee Research, an owner-gated autonomous research lab. The content synthesizes findings from peer-reviewed papers. Tribunal score: 7.8/10.