Research map / Label-efficient and robust learning / Recognition and long-tail
Exploring Multiple Feature Spaces for Novel Entity Discovery
Zhaohui Wu, Yang Song, C. Giles
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 Novel Entity Model instead of D2W | novel entity classifier · WebNews | precision: 61.35 -> 91.94 | Improved |
| use Novel Entity Model instead of D2W | novel entity classifier · WebNews | recall: 80.53 -> 70.27 | Hurt |
| use Novel Entity Model instead of EE | novel entity classifier · WikiEvents | F1: 64.67 -> 77.37 | Improved |
| use Novel Entity Model instead of D2W | novel entity classifier · AIDA-EE | F1: 63.89 -> 71.92 | Improved |
| add each feature space (contextual, ODP, lexical, embedding, query) to the classifier (ablation) | Novel Entity Model · WebNews | precision, recall, F1 | Improved |
| add contextual and topical spaces rather than lexical, embedding, query (ablation) | Novel Entity Model · WebNews | F1 | Improved |
| train on top-K candidates with K=3 instead of other K (ablation) | Novel Entity Model · WebNews | precision, recall, F1 | No clear effect |
| add Novel Entity Classifier as preprocessing to p(et|t) linker | entity linking · WebNews | linking accuracy: 74.06 -> 77.33 | Improved |
| add Novel Entity Classifier as preprocessing to Context linker | entity linking · WebNews | linking accuracy: 78.38 -> 81.17 | Improved |
| add Novel Entity Classifier as preprocessing to Cucerzan's linker | entity linking · WebNews | linking accuracy: 78.85 -> 81.93 | Improved |
| add Novel Entity Classifier as preprocessing to Cucerzan's linker | entity linking · WikiEvents | linking accuracy: 79.36 -> 80.75 | Improved |
| add Novel Entity Classifier as preprocessing to Context linker | entity linking · AIDA-EE | linking accuracy: 76.27 -> 77.20 | Improved |
Closest papers by meaning
- Leveraging Multi-Token Entities in Document-Level Named Entity Recognition (AAAI 2020 · similarity 0.86)
- Fine-Grained Entity Typing for Domain Independent Entity Linking (AAAI 2020 · similarity 0.86)
- Revisiting Document-Level Relation Extraction with Context-Guided Link Prediction (AAAI 2024 · similarity 0.85)
- Knowledge Graph Completion with Relation-Aware Anchor Enhancement (AAAI 2025 · similarity 0.84)
- Select and Augment: Enhanced Dense Retrieval Knowledge Graph Augmentation (Abstract Reprint) (AAAI 2024 · similarity 0.84)
- Three Heads Are Better than One: Improving Cross-Domain NER with Progressive Decomposed Network (AAAI 2024 · similarity 0.83)
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.
