Cross-lingual NER Fine-tuning with Synthetic Parallel Corpora for Low-Resource Language Robustness

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 fine-tuning a projection-based cross-lingual NER model on synthetic parallel corpora improve robustness against morphosyntactic variations in low-resource languages, as evaluated using the SIGMORPHON dataset?

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