Research map / Architectures and efficiency / RNNs and normalization
GRN: Gated Relation Network to Enhance Convolutional Neural Network for Named Entity Recognition
Hui Chen, Zijia Lin, Guiguang Ding, Jianguang Lou, Yusen Zhang, Borje Karlsson
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 multi-scale context branches (ablation) | GRN · CoNLL-2003 | F1: 88.36 ± 0.21 -> 91.44 ± 0.16 | Improved |
| Use multi-scale context branches rather than only the kernel-size-3 branch (ablation) | GRN · CoNLL-2003 | F1: 90.88 ± 0.22 -> 91.44 ± 0.16 | Improved |
| Add the relation layer (ablation) | GRN · CoNLL-2003 | F1: 90.13 ± 0.28 -> 91.44 ± 0.16 | Improved |
| Use channel-wise gated relation fusion rather than direct averaging (ablation) | GRN · CoNLL-2003 | F1: 90.72 ± 0.06 -> 91.44 ± 0.16 | Improved |
| Use channel-wise gating rather than gated attention (ablation) | GRN · CoNLL-2003 | F1: 87.11 ± 0.25 -> 91.44 ± 0.16 | Improved |
| Add multi-scale context branches (ablation) | GRN · OntoNotes 5.0 | F1: 82.21 ± 0.23 -> 87.67 ± 0.17 | Improved |
| Use multi-scale context branches rather than only the kernel-size-3 branch (ablation) | GRN · OntoNotes 5.0 | F1: 86.66 ± 0.21 -> 87.67 ± 0.17 | Improved |
| Add the relation layer (ablation) | GRN · OntoNotes 5.0 | F1: 85.87 ± 0.16 -> 87.67 ± 0.17 | Improved |
| Use channel-wise gated relation fusion rather than direct averaging (ablation) | GRN · OntoNotes 5.0 | F1: 85.81 ± 0.14 -> 87.67 ± 0.17 | Improved |
| Use channel-wise gating rather than gated attention (ablation) | GRN · OntoNotes 5.0 | F1: 79.83 ± 0.37 -> 87.67 ± 0.17 | Improved |
| Use GRN instead of CNN-BiLSTM-CRF | NER system · CoNLL-2003 | training speedup: 1.16x | Improved |
| Use GRN instead of CNN-BiLSTM-CRF | NER system · CoNLL-2003 | test speedup: 1.19x | Improved |
Closest papers by meaning
- Unified Named Entity Recognition as Word-Word Relation Classification (AAAI 2022 · similarity 0.88)
- Deep Active Learning for Named Entity Recognition (ICLR 2018 · similarity 0.88)
- Adversity-aware Few-shot Named Entity Recognition via Augmentation Learning (AAAI 2025 · similarity 0.85)
- UniversalNER: Targeted Distillation from Large Language Models for Open Named Entity Recognition (ICLR 2024 · similarity 0.84)
- PaDeLLM-NER: Parallel Decoding in Large Language Models for Named Entity Recognition (NeurIPS 2024 · similarity 0.84)
- SENCR: A Span Enhanced Two-Stage Network with Counterfactual Rethinking for Chinese NER (AAAI 2024 · similarity 0.84)
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.
