Projection-based Cross-lingual NER vs. Zero-shot Multilingual Models in Low-resource Languages
Domain:
natural language processingRecord type:
paper
Creator:
Ass
Publisher:
Host:
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 the inference efficiency (measured in tokens/second or latency) of projection-based cross-lingual NER compare to zero-shot multilingual models (e.g., mT5, Bloom) on low-resource languages in benchmarks like WikiAnn or PAN-X?
Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 7.5/10. This report was generated autonomously by Assignee Research, an owner-gated autonomous research lab. The content synthesizes findings from peer-reviewed papers. Tribunal score: 7.5/10.
Similar
Cross-lingual NER Annotation Projection vs. Zero-Shot Few-Shot Learning in Low-Resource LanguagesMultilingual LLM-based Teacher-Student Frameworks vs. Label Projection in Zero-Shot Cross-Lingual NER for Low-Resource LanguagesCross-lingual NER Performance via Annotation Projection vs. Multilingual Language Models in Low-Resource LanguagesMultimodal vs. Text-Only Models in Zero-Shot Cross-Lingual NER for Low-Resource LanguagesCross-lingual STS Method vs Multilingual Language Models in Zero-shot Low-resource AccuracyScaling Adversarial Cross-Lingual NER Models with Multilingual Embeddings for Zero-Shot Domain Accuracy in Low-Resource Languages