Multi-source Teacher Ensembles for Rare Entity NER 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: Do multi-source teacher ensembles outperform single-source teachers in few-shot cross-lingual NER settings when evaluated on the NER accuracy of rare entity types in low-resource languages within the UDA-NER dataset?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 7.6/10.