Research map / Label-efficient and robust learning / Recognition and long-tail
Zero-Resource Cross-Lingual Named Entity Recognition
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Add augmented fine-tuning with source guidance and target pseudo-labels to Cross-Shared (ablation) | Cross-lingual NER · English→Spanish, Dutch, German, Arabic, Finnish | F1: +2.43, +2.21, +6.14, +7.1, +5.73 F1 | Helped |
| Share forward and backward LSTM weights (ablation) | Cross-Word · English→Spanish | F1: +1.73 | Helped |
| Share forward and backward LSTM weights (ablation) | Cross-Word · English→Dutch | F1: +0.71 | Helped |
| Share forward and backward LSTM weights (ablation) | Cross-Word · English→Arabic | F1: 28.28 ± 1.61 -> 23.32 ± 0.76 | Hurt |
| Share forward and backward LSTM weights (ablation) | Cross-Word · English→German and English→Finnish | F1 | No clear effect |
| Use pretrained source character embeddings (ablation) | Cross-lingual NER · English→Spanish, Dutch, Finnish | F1 | Helped |
| Use pretrained source character embeddings (ablation) | Cross-lingual NER · English→Arabic | F1 | Hurt |
| Use pretrained source character embeddings (ablation) | Cross-lingual NER · English→German | F1 | Hurt |
| Replace monolingual word embeddings with random word embeddings (ablation) | Source-Mono · Cross-lingual target NER | F1 | Helped |
| Use BPE subword units instead of shared character embeddings (ablation) | Cross-lingual NER · Cross-lingual target NER | F1 | No clear effect |
| Increase the maximum sentence length used for pseudo-label training (ablation) | Cross-Augmented · Target-language NER | correctly tagged sentences | Hurt |
Closest papers by meaning
- MCL-NER: Cross-Lingual Named Entity Recognition via Multi-View Contrastive Learning (AAAI 2024 · similarity 0.91)
- Three Heads Are Better than One: Improving Cross-Domain NER with Progressive Decomposed Network (AAAI 2024 · similarity 0.88)
- Adversity-aware Few-shot Named Entity Recognition via Augmentation Learning (AAAI 2025 · similarity 0.87)
- UniversalNER: Targeted Distillation from Large Language Models for Open Named Entity Recognition (ICLR 2024 · similarity 0.87)
- Discrepancy and Uncertainty Aware Denoising Knowledge Distillation for Zero-Shot Cross-Lingual Named Entity Recognition (AAAI 2024 · similarity 0.86)
- PaDeLLM-NER: Parallel Decoding in Large Language Models for Named Entity Recognition (NeurIPS 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.