Projection-based Cross-lingual NER Scaling and F1-Score Gaps in Low-Resource Languages

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 pres

Research goal: What is the impact of scaling the training data size in projection-based cross-lingual NER on the F1-score performance gap between low-resource languages and high-resource languages, as compared to fine-tuned mT5 models on XTREME-R benchmarks?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.4/10.