Cross-lingual NER Projection with CLIP Visual Embeddings vs Text-only Methods on CoNLL-2003

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: How does incorporating CLIP-based visual embeddings into cross-lingual NER projection compare in accuracy to traditional text-only methods when evaluated on the CoNLL-2003 benchmark for low-resource languages?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.5/10.