Research map / Label-efficient and robust learning / Recognition and long-tail
Enhanced Meta-Learning for Cross-Lingual Named Entity Recognition with Minimal Resources
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 |
|---|---|---|---|
| Use enhanced meta-learning with retrieved similar source examples for per-example adaptation | mBERT cross-lingual NER · Cross-lingual NER average (five target languages) | F1: 70.45 -> 72.71 | Helped |
| Add the maximum-loss term during meta-training (ablation) | Enhanced meta-learning for cross-lingual NER · Cross-lingual NER average (five target languages) | F1: 71.36 -> 72.71; +1.35 | Helped |
| Add entity masking during meta-training (ablation) | Enhanced meta-learning for cross-lingual NER · CoNLL-2002 Spanish testb | F1: 75.57 -> 76.75; +1.18 | Helped |
| Add both max loss and entity masking (ablation) | Meta-learning cross-lingual NER · Cross-lingual NER average (five target languages) | F1: 71.25 -> 72.71; +1.46 | Helped |
| Add meta-training and per-example adaptation (ablation) | mBERT cross-lingual NER · Europeana Newspapers French test | F1: 50.89 -> 55.30; +4.41 | Helped |
| Use the augmented max-loss function during adaptation instead of the standard loss | Adaptation phase of the proposed method · Cross-lingual NER | F1 | Mixed |
Closest papers by meaning
- Zero-Resource Cross-Lingual Named Entity Recognition (AAAI 2020 · similarity 0.92)
- MCL-NER: Cross-Lingual Named Entity Recognition via Multi-View Contrastive Learning (AAAI 2024 · similarity 0.91)
- ProKD: An Unsupervised Prototypical Knowledge Distillation Network for Zero-Resource Cross-Lingual Named Entity Recognition (AAAI 2023 · similarity 0.91)
- Three Heads Are Better than One: Improving Cross-Domain NER with Progressive Decomposed Network (AAAI 2024 · similarity 0.87)
- UniversalNER: Targeted Distillation from Large Language Models for Open Named Entity Recognition (ICLR 2024 · similarity 0.87)
- GuideNER: Annotation Guidelines Are Better than Examples for In-Context Named Entity Recognition (AAAI 2025 · 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.