Multimodal Teacher-Student Learning for Cross-Lingual Entity Recognition 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: Can the teacher-student learning approach for cross-lingual NER be extended to incorporate multimodal inputs (e.g., text + images) and evaluated on benchmarks like MMMM or LVIS for entity recognition in low-resource languages?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.0/10.