Research map / Label-efficient and robust learning / Recognition and long-tail
Debiased and Denoised Entity Recognition from Distant Supervision
Haobo Wang, Yiwen Dong, Ruixuan Xiao, Fei Huang, Gang Chen, Junbo Zhao
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 |
|---|---|---|---|
| Remove WCE loss (ablation) | DesERT · CoNLL03 | F1: 85.50 -> 86.75 | Improved |
| Add dual-network co-guessing (ablation) | DesERT · CoNLL03 | F1: 83.44 -> 86.75 | Improved |
| Use double-head pathway instead of single head (ablation) | DesERT · CoNLL03 | F1: 84.54 -> 86.75 | Improved |
| Double-head pathway on minority class MISC (ablation) | DesERT · CoNLL03 MISC | F1: +7.11% | Improved |
| Double-head pathway on LOC entities (ablation) | DesERT · CoNLL03 LOC | F1: +2.91% | Improved |
| Add post-hoc entity pathway finetuning | DesERT · CoNLL03 | F1: 86.75 -> 86.95 | Improved |
| Add post-hoc entity pathway finetuning | DesERT · Webpage | F1: 72.24 -> 72.73 | Improved |
| Use DesERT instead of SCDL | SCDL · Webpage | F1: 68.47 -> 72.24 | Improved |
| Use DesERT instead of SCDL | SCDL · Wikigold | F1: 64.13 -> 64.23 | No clear effect |
| Lower confidence threshold tau below 0.95 | DesERT · CoNLL03 | F1 | Hurt |
| Vary co-guessing start epoch k from 15 to 40 | DesERT · CoNLL03 | F1: 86.72 -> 86.18 | No clear effect |
| Vary co-guessing start epoch k from 15 to 40 | DesERT · Twitter | F1: 52.22 -> 51.54 | No clear effect |
Closest papers by meaning
- UniversalNER: Targeted Distillation from Large Language Models for Open Named Entity Recognition (ICLR 2024 · similarity 0.86)
- Discrepancy and Uncertainty Aware Denoising Knowledge Distillation for Zero-Shot Cross-Lingual Named Entity Recognition (AAAI 2024 · similarity 0.86)
- Small Language Model Makes an Effective Long Text Extractor (AAAI 2025 · similarity 0.85)
- MCL-NER: Cross-Lingual Named Entity Recognition via Multi-View Contrastive Learning (AAAI 2024 · similarity 0.85)
- GuideNER: Annotation Guidelines Are Better than Examples for In-Context Named Entity Recognition (AAAI 2025 · similarity 0.85)
- PaDeLLM-NER: Parallel Decoding in Large Language Models for Named Entity Recognition (NeurIPS 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.
