Research map / Label-efficient and robust learning / Recognition and long-tail
Leveraging Multi-Token Entities in Document-Level Named Entity Recognition
Anwen Hu, Zhicheng Dou, Jian-Yun Nie, Ji-Rong Wen
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 |
|---|---|---|---|
| add document-level representation to sentence-level model (ablation) | SENT · CoNLL-2003 | F1: 90.92 -> 91.92 | Improved |
| add ME-informed attention (multi-token entity information) (ablation) | MEID-ME · CoNLL-2003 | F1: 91.78 -> 91.92 | Improved |
| add ME-informed attention (ablation) | MEID-ME · OntoNotes-nbm | F1: 88.84 -> 89.16 | Improved |
| add semantic attention to ME attention (ablation) | MEID-SEM · CoNLL-2003 | F1: 91.71 -> 91.92 | Improved |
| add semantic attention to ME attention (ablation) | MEID-SEM · OntoNotes-nbm | F1: 88.71 -> 89.16 | Improved |
| replace gate and BiLSTM fusion (GlobalAtt) with a single MLP (ablation) | MEID-ME vs GlobalAtt · CoNLL-2003 | F1: 91.43 -> 91.78 | No clear effect |
| add MEID document-level module on bert-base embeddings (ablation) | SENT · CoNLL-2003 | F1: 90.66 -> 91.47 | Improved |
| add MEID document-level module on flair embeddings (ablation) | SENT · OntoNotes-nbm | F1: 89.89 -> 90.29 | Improved |
| train multi-token entity classification jointly with NER (ablation) | MEC task · CoNLL-2003 | F1: 95.89 -> 96.20 | Improved |
| add ME part on conversational documents (ablation) | MEID · OntoNotes-c | F1: 75.17 -> 74.89 | Hurt |
Closest papers by meaning
- Span Graph Transformer for Document-Level Named Entity Recognition (AAAI 2024 · similarity 0.89)
- MCL-NER: Cross-Lingual Named Entity Recognition via Multi-View Contrastive Learning (AAAI 2024 · similarity 0.88)
- Small Language Model Makes an Effective Long Text Extractor (AAAI 2025 · similarity 0.87)
- ConsistNER: Towards Instructive NER Demonstrations for LLMs with the Consistency of Ontology and Context (AAAI 2024 · similarity 0.87)
- GuideNER: Annotation Guidelines Are Better than Examples for In-Context Named Entity Recognition (AAAI 2025 · similarity 0.87)
- Multi-Grained Query-Guided Set Prediction Network for Grounded Multimodal Named Entity Recognition (AAAI 2025 · similarity 0.87)
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.
