Research map / Label-efficient and robust learning / Knowledge distillation
Distantly-Supervised Named Entity Recognition with Adaptive Teacher Learning and Fine-Grained Student Ensemble
Xiaoye Qu, Jun Zeng, Daizong Liu, Zhefeng Wang, Baoxing Huai, Pan Zhou
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 ATSEN instead of SCDL | DS-NER · CoNLL03 | F1: 83.69 -> 85.59 | Improved |
| use ATSEN instead of SCDL | DS-NER · OntoNotes 5.0 | F1: 68.61 -> 68.95 | Improved |
| use ATSEN instead of SCDL | DS-NER · Webpage | F1: 68.47 -> 70.55 | Improved |
| use ATSEN instead of SCDL | DS-NER · Twitter | F1: 51.09 -> 52.46 | Improved |
| add consistent prediction (CP) (ablation) | ATSEN · CoNLL03 | F1: 82.56 -> 85.59 | Improved |
| add threshold prediction (TP) (ablation) | ATSEN · CoNLL03 | F1: 83.54 -> 85.59 | Improved |
| add cross-entropy loss (CE) (ablation) | ATSEN · CoNLL03 | F1: 85.20 -> 85.59 | Improved |
| add adaptive distillation (AD) (ablation) | ATSEN · CoNLL03 | F1: 84.95 -> 85.59 | Improved |
| add fine-grained ensemble (FE) (ablation) | ATSEN · CoNLL03 | F1: 84.11 -> 85.59 | Improved |
| use adaptive rather than average distillation (ablation) | ATSEN student training · CoNLL03 | F1: 85.19 -> 85.59 | Improved |
| use adaptive rather than manually weighted distillation (ablation) | ATSEN student training · CoNLL03 | F1: 85.22 -> 85.59 | Improved |
| use adaptive rather than dynamically weighted distillation (ablation) | ATSEN student training · CoNLL03 | F1: 85.26 -> 85.59 | Improved |
Closest papers by meaning
- Debiased and Denoised Entity Recognition from Distant Supervision (NeurIPS 2023 · similarity 0.90)
- UniversalNER: Targeted Distillation from Large Language Models for Open Named Entity Recognition (ICLR 2024 · similarity 0.87)
- Span Graph Transformer for Document-Level Named Entity Recognition (AAAI 2024 · similarity 0.86)
- GuideNER: Annotation Guidelines Are Better than Examples for In-Context Named Entity Recognition (AAAI 2025 · similarity 0.86)
- Unify Named Entity Recognition Scenarios via Contrastive Real-Time Updating Prototype (AAAI 2024 · similarity 0.86)
- ConsistNER: Towards Instructive NER Demonstrations for LLMs with the Consistency of Ontology and Context (AAAI 2024 · similarity 0.85)
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.
