Research map / Label-efficient and robust learning / Recognition and long-tail
Recursively Binary Modification Model for Nested Named Entity Recognition
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 |
|---|---|---|---|
| add modification probabilities (head inference) (ablation) | RBM · GENIA | F1 (%): 77.7 -> 79.8 | Helped |
| add modification probabilities (head inference) (ablation) | RBM · ACE2005 | F1 (%): 72.8 -> 73.6 | Helped |
| add pretrained embeddings (ablation) | RBM · GENIA | F1 (%): 74.4 -> 79.8 | Helped |
| add pretrained embeddings (ablation) | RBM · ACE2005 | F1 (%): 71.5 -> 73.6 | Helped |
| add character-level embeddings (ablation) | RBM · GENIA | F1 (%): 66.1 -> 79.8 | Helped |
| add character-level embeddings (ablation) | RBM · ACE2005 | F1 (%): 66.6 -> 73.6 | Helped |
| replace span-average representation with RBM head-based typing (ablation) | Sohrab and Miwa span model · GENIA | F1 (%): 77.1 -> 79.8 | Helped |
| RBM vs span-average on nested entities (ablation) | Sohrab and Miwa span model · GENIA nested entities | F1 (%): 72.7 -> 83.1 | Helped |
| RBM vs span-average on single-token entities (ablation) | Sohrab and Miwa span model · GENIA single-token | F1 (%): 69.9 -> 81.8 | Helped |
| RBM vs span-average on CELL-TYPE category (ablation) | Sohrab and Miwa span model · GENIA CELL-TYPE | F1 (%): 78.1 -> 76.8 | Hurt |
| RBM vs span-average on DNA category (ablation) | Sohrab and Miwa span model · GENIA DNA | F1 (%): 71.8 -> 75.0 | Helped |
| lower undersampling rate m=15 instead of 25 (ablation) | RBM · ACE2005 | F1 (%): 73.6 -> 73.4 | No clear effect |
Closest papers by meaning
- Knowledge-aware Named Entity Recognition with Alleviating Heterogeneity (AAAI 2021 · similarity 0.89)
- Span Graph Transformer for Document-Level Named Entity Recognition (AAAI 2024 · similarity 0.87)
- MCL-NER: Cross-Lingual Named Entity Recognition via Multi-View Contrastive Learning (AAAI 2024 · similarity 0.87)
- UniversalNER: Targeted Distillation from Large Language Models for Open Named Entity Recognition (ICLR 2024 · similarity 0.86)
- GuideNER: Annotation Guidelines Are Better than Examples for In-Context Named Entity Recognition (AAAI 2025 · similarity 0.86)
- A Reasoning Paradigm for Named Entity Recognition (AAAI 2026 · 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.