Research map / Label-efficient and robust learning / Recognition and long-tail
Unified Named Entity Recognition as Word-Word Relation Classification
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 region embeddings (ablation) | W²NER · CoNLL2003, ACE2005, CADEC | F1: 92.80 (-0.27); 86.39 (-0.40); 72.56 (-0.65) | Helped |
| Remove distance embeddings (ablation) | W²NER · CoNLL2003, ACE2005, CADEC | F1: 92.89 (-0.18); 86.47 (-0.32); 72.66 (-0.55) | Helped |
| Remove all dilated convolutions (ablation) | W²NER · CoNLL2003, ACE2005, CADEC | F1: 92.31 (-0.76); 86.07 (-0.72); 72.45 (-0.76) | Helped |
| Remove DConv (l=1) (ablation) | W²NER · CoNLL2003, ACE2005, CADEC | F1: 93.05 (-0.02); 86.64 (-0.15); 73.12 (-0.09) | Helped |
| Remove DConv (l=2) (ablation) | W²NER · CoNLL2003, ACE2005, CADEC | F1: 92.78 (-0.29); 86.58 (-0.21); 72.95 (-0.26) | Helped |
| Remove DConv (l=3) (ablation) | W²NER · CoNLL2003, ACE2005, CADEC | F1: 92.82 (-0.25); 86.59 (-0.20); 73.10 (-0.11) | Helped |
| Remove biaffine predictor (ablation) | W²NER · CoNLL2003, ACE2005, CADEC | F1: 93.02 (-0.05); 86.30 (-0.49); 72.71 (-0.50) | Helped |
| Remove MLP predictor (ablation) | W²NER · CoNLL2003, ACE2005, CADEC | F1: 91.87 (-1.20); 85.66 (-1.13); 68.04 (-5.17) | Helped |
| Remove NNW relation (ablation) | W²NER · CoNLL2003, ACE2005, CADEC | F1: 92.65 (-0.42); 86.23 (-0.56); 69.01 (-4.20) | Helped |
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)
- UniversalNER: Targeted Distillation from Large Language Models for Open Named Entity Recognition (ICLR 2024 · similarity 0.88)
- SENCR: A Span Enhanced Two-Stage Network with Counterfactual Rethinking for Chinese NER (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)
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.