Research map / Label-efficient and robust learning / Recognition and long-tail
A Supervised Multi-Head Self-Attention Network for Nested Named Entity Recognition
Yongxiu Xu, Heyan Huang, Chong Feng, Yue Hu
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 supervised multi-head self-attention with BERT embeddings instead of Tan et al. (2020) (BERT) | Nested NER · ACE2004 | F1: 1.0% | Improved |
| use supervised multi-head self-attention with BERT embeddings instead of Tan et al. (2020) (BERT) | Nested NER · ACE2005 | F1: 1.5% | Improved |
| use supervised multi-head self-attention with SciBERT embeddings instead of Tan et al. (2020) (BERT) | Nested NER · GENIA | F1: 1.3% | Improved |
| use supervised multi-head self-attention with SciBERT embeddings instead of Tan et al. (2020) (BERT) | Flat NER · JNLPBA | F1: 1.1% | Improved |
| use supervised multi-head self-attention with BERT embeddings instead of the seq2seq-BERT baseline | Flat NER · CoNLL03-English | F1: 1.7% | Improved |
| replace SciBERTbase with BERTbase (ablation) | MHSA-BERT on GENIA · GENIA | F1: 79.6 -> 77.8(↓1.8) | Hurt |
| add the boundary detection module (ablation) | MHSA-BERT on GENIA · GENIA | F1: 78.6 -> 79.6 | Improved |
| add a pre-trained language model (ablation) | MHSA on GENIA · GENIA | F1: 77.3 -> 79.6 | Improved |
| add character-level embeddings (ablation) | MHSA-BERT on GENIA · GENIA | F1: 79.1 -> 79.6 | Improved |
Closest papers by meaning
- Leveraging Multi-Token Entities in Document-Level Named Entity Recognition (AAAI 2020 · similarity 0.90)
- Multi-Grained Query-Guided Set Prediction Network for Grounded Multimodal 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)
- Small Language Model Makes an Effective Long Text Extractor (AAAI 2025 · similarity 0.86)
- Span Graph Transformer for Document-Level Named Entity Recognition (AAAI 2024 · similarity 0.85)
- GuideNER: Annotation Guidelines Are Better than Examples for In-Context Named Entity Recognition (AAAI 2025 · 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.
