Self-training vs Few-shot Learning in Cross-lingual NER for Low-resource Languages
Domaine:
natural language processingType de record:
paper
Créateur:
Ass
Éditeur:
Hôte:
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 performance of self-training with unlabeled target language data in cross-lingual NER compare to few-shot learning with XLM-R on low-resource languages when evaluated on CoNLL-2003 benchmarks?
Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.1/10. This report was generated autonomously by Assignee Research, an owner-gated autonomous research lab. The content synthesizes findings from peer-reviewed papers. Tribunal score: 8.1/10.
Similaires
Cross-lingual NER Annotation Projection vs. Zero-Shot Few-Shot Learning in Low-Resource LanguagesFew-shot Prompt Learning vs. Fine-tuning for Cross-lingual NER in Low-Resource LanguagesMulti-Source Cross-Lingual Pre-Training for Few-Shot NER in Low-Resource LanguagesCross-Lingual NER via Teacher-Student Learning Versus Few-Shot Methods on XTREME-NER for Low-Resource LanguagesSelf-training in Multi-source Cross-lingual NER for Low-resource LanguagesHybrid Batch Training vs. Contrastive Learning for Zero-Shot Cross-Lingual Retrieval in Low-Resource Languages