Research map / Label-efficient and robust learning / Recognition and long-tail
HAMNER: Headword Amplified Multi-Span Distantly Supervised Method for Domain Specific Named Entity Recognition
Shifeng Liu, Yifang Sun, Bing Li, Wei Wang, Xiang 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 |
|---|---|---|---|
| extend the dictionary with headword-based semantic matches (ablation) | HAMNER pseudo-annotation generation · BC5CDR training annotations | recall: 72.23 -> 84.48 | Improved |
| extend the dictionary with headword-based semantic matches (ablation) | HAMNER pseudo-annotation generation · NCBI-Disease training annotations | recall: 60.56 -> 83.01 | Improved |
| extend the dictionary with headword-based semantic matches (ablation) | HAMNER pseudo-annotation generation · LaptopReview training annotations | recall: 51.65 -> 54.51 | Improved |
| extend the dictionary with headword-based semantic matches (ablation) | HAMNER pseudo-annotation generation · BC5CDR training annotations | precision: 94.92 -> 91.89 | Hurt |
| extend the dictionary with headword-based semantic matches (ablation) | HAMNER pseudo-annotation generation · NCBI-Disease training annotations | precision: 93.88 -> 92.61 | Hurt |
| extend the dictionary with headword-based semantic matches (ablation) | HAMNER pseudo-annotation generation · LaptopReview training annotations | precision: 89.01 -> 87.73 | Hurt |
| add similarity-based weights to extended-dictionary annotations (ablation) | HAMNER · BC5CDR | precision: +0.55% | Improved |
| add similarity-based weights to extended-dictionary annotations (ablation) | HAMNER · NCBI-Disease | precision: +1.4% | Improved |
| add similarity-based weights to extended-dictionary annotations (ablation) | HAMNER · BC5CDR and NCBI-Disease | recall | Hurt |
| add similarity-based weights to extended-dictionary annotations (ablation) | HAMNER · LaptopReview | F1 | No clear effect |
| add dictionary extension (ablation) | HAMNER span-level model · NCBI-Disease | precision: +0.58% | Improved |
| add dictionary extension (ablation) | HAMNER span-level model · NCBI-Disease | recall: +5.25% | Improved |
Closest papers by meaning
- Span Graph Transformer for Document-Level Named Entity Recognition (AAAI 2024 · similarity 0.89)
- Small Language Model Makes an Effective Long Text Extractor (AAAI 2025 · similarity 0.89)
- UniversalNER: Targeted Distillation from Large Language Models for Open Named Entity Recognition (ICLR 2024 · similarity 0.87)
- Multi-Grained Query-Guided Set Prediction Network for Grounded Multimodal Named Entity Recognition (AAAI 2025 · similarity 0.86)
- GuideNER: Annotation Guidelines Are Better than Examples for In-Context Named Entity Recognition (AAAI 2025 · similarity 0.86)
- MCL-NER: Cross-Lingual Named Entity Recognition via Multi-View Contrastive Learning (AAAI 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.
