Research map / Label-efficient and robust learning / Recognition and long-tail
A Recurrent Model for Collective Entity Linking with Adaptive Features
Xiaoling Zhou, Yukai Miao, Wei Wang, Jianbin Qin
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 recurrent global iterations over the initial global model (ablation) | RMA · AIDA-B | in-KB accuracy: 89.8 -> 91.5 | Improved |
| add local adaptive features to the initial global model (ablation) | RMA · AIDA-B | in-KB accuracy: 87.5 -> 89.8 | Improved |
| add coherence features (initial global model) to the local model (ablation) | RMA · AIDA-B | in-KB accuracy: 85.7 -> 87.5 | Improved |
| add novel local features on top of prior-only model (ablation) | RMA local model · AIDA-B | in-KB accuracy: 68.2 -> 85.7 | Improved |
| gold-entity mention prior bucket from <=0.01 to >0.30 | RMA · AIDA-B | in-KB accuracy: 57.34% -> 97.94% | Improved |
| gold-entity prior 0.03-0.10 vs 0.01-0.03 | RMA · AIDA-B | in-KB accuracy: 80.58% -> 75.18% | Hurt |
| compare RMA against Le and Titov 2018 on WIKI | RMA · WIKI | Micro-F1: 78.0 -> 82.2 | Improved |
| compare RMA against Le and Titov 2018 on MSB | RMA · MSB | Micro-F1: 93.9 -> 93.2 | Hurt |
| compare RMA against Ganea and Hofmann 2017 on CWEB | RMA · CWEB | Micro-F1: 77.9 -> 79.3 | Improved |
| compare RMA against Guo and Barbosa 2018 on WIKI | RMA · WIKI | Micro-F1: 84.5 -> 82.2 | Hurt |
| compare RMA against Le and Titov 2018 on AIDA-B | RMA · AIDA-B | in-KB accuracy: 93.1 -> 91.5 | Hurt |
| compare RMA against Hoffart et al. 2011 on AIDA-B | RMA · AIDA-B | in-KB accuracy: 78.0 -> 91.5 | Improved |
Closest papers by meaning
- Task-Specific Representation Learning for Web-Scale Entity Disambiguation (AAAI 2018 · similarity 0.90)
- Fine-Grained Entity Typing for Domain Independent Entity Linking (AAAI 2020 · similarity 0.88)
- Mention and Entity Description Co-Attention for Entity Disambiguation (AAAI 2018 · similarity 0.86)
- HAMNER: Headword Amplified Multi-Span Distantly Supervised Method for Domain Specific Named Entity Recognition (AAAI 2020 · similarity 0.86)
- Continual Learning for Named Entity Recognition (AAAI 2021 · similarity 0.86)
- UniversalNER: Targeted Distillation from Large Language Models for Open Named Entity Recognition (ICLR 2024 · similarity 0.85)
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.
