Research map / Architectures and efficiency / RNNs and normalization
End-to-End Bootstrapping Neural Network for Entity Set Expansion
Lingyong Yan, Xianpei Han, Ben He, Le Sun
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 BootstrapNet instead of pipelined bootstrapping baselines | BootstrapNet · CoNLL | precision after 20 iterations: less than 70% -> higher than 80% | Improved |
| Use BootstrapNet instead of pipelined bootstrapping baselines | BootstrapNet · OntoNotes | precision after 20 iterations: less than 40% -> higher than 45% | Improved |
| Add the BootstrapEncoder (graph attention) (ablation) | BootstrapNet · CoNLL and OntoNotes | precision vs throughput | Improved |
| Add the BootstrapDecoder (GRU sequential expansion) (ablation) | BootstrapNet · CoNLL and OntoNotes | precision vs throughput | Improved |
| Remove both encoder and decoder (ablation) | BootstrapNet · CoNLL and OntoNotes | precision vs throughput | Hurt |
| Increase encoder layers from 1 to 3 (ablation) | BootstrapEncoder · CoNLL | precision vs throughput | Improved |
| Increase encoder layers from 1 to 3 (ablation) | BootstrapEncoder · OntoNotes | precision vs throughput | Improved |
| Increase encoder layers from 0 to 1 (ablation) | BootstrapEncoder · CoNLL and OntoNotes | precision vs throughput | Improved |
| Replace GloVe initialization with random initialization (ablation) | BootstrapNet · CoNLL | precision @10 iters: .882 -> .405 | Hurt |
| Replace GloVe initialization with random initialization (ablation) | BootstrapNet · CoNLL | precision @20 iters: .808 -> .385 | Hurt |
| Replace GloVe initialization with random initialization (ablation) | BootstrapNet · OntoNotes | precision @10 iters: .521 -> .226 | Hurt |
| Replace GloVe initialization with random initialization (ablation) | BootstrapNet · OntoNotes | precision @20 iters: .431 -> .206 | Hurt |
Closest papers by meaning
- MESED: A Multi-Modal Entity Set Expansion Dataset with Fine-Grained Semantic Classes and Hard Negative Entities (AAAI 2024 · similarity 0.83)
- UniversalNER: Targeted Distillation from Large Language Models for Open Named Entity Recognition (ICLR 2024 · similarity 0.82)
- Revisit and Outstrip Entity Alignment: A Perspective of Generative Models (ICLR 2024 · similarity 0.82)
- Multi-Grained Query-Guided Set Prediction Network for Grounded Multimodal Named Entity Recognition (AAAI 2025 · similarity 0.82)
- Three Heads Are Better than One: Improving Cross-Domain NER with Progressive Decomposed Network (AAAI 2024 · similarity 0.82)
- MCL-NER: Cross-Lingual Named Entity Recognition via Multi-View Contrastive Learning (AAAI 2024 · similarity 0.82)
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.
