Cross-lingual NER Performance via Intermediate Language Alignment in Low-resource Settings

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: To what extent does domain adaptation via intermediate language alignment (e.g., pivoting through a high-resource language) improve cross-lingual NER performance compared to direct projection methods in low-resource settings with synthetic noise?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 7.9/10.