Research map / Graph learning / Knowledge and temporal graphs
Knowledge-Graph Augmented Word Representations for Named Entity Recognition
Qizhen He, Liang Wu, Yida Yin, Heming Cai
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 KG entity embedding (GERU) and relation attention to BERT, FC head | BERT-FC · 5 NER datasets | F1: +0.46 to +2.07 | Improved |
| add KAWR to BERT with BiLSTM-CRF head | BERT+BiLSTM+CRF · 5 NER datasets | F1: +0.21 to +2.86 | Improved |
| add GERU entity embedding (ablation) | BERT · SEC | F1: 80.22 -> 82.58 | Improved |
| use GERU instead of averaging related entity embeddings (ablation) | BERT+EntityEmbedding · SEC | F1: 80.59 -> 82.58 | Improved |
| add relation attention embedding (ablation) | BERT · SEC | F1: 80.22 -> 81.09 | Improved |
| combine entity and relation embeddings (ablation) | BERT+EntityEmbedding · SEC | F1: 82.58 -> 83.08 | Improved |
| KAWR on unseen entities | BERT-FC · SEC unseen entities | F1: 49.49 -> 58.88 | Improved |
| KAWR on other languages | BERT-FC · German/Spanish/Dutch | F1: +0.12 to +1.12 | Improved |
| KAWR on small training sets | BERT-FC · SEC, WNUT16 | F1: 79.03 -> 81.1 (SEC) | Improved |
Closest papers by meaning
- Select and Augment: Enhanced Dense Retrieval Knowledge Graph Augmentation (Abstract Reprint) (AAAI 2024 · similarity 0.87)
- Hierarchical Contextualized Representation for Named Entity Recognition (AAAI 2020 · similarity 0.86)
- Span Graph Transformer for Document-Level Named Entity Recognition (AAAI 2024 · similarity 0.85)
- MKGL: Mastery of a Three-Word Language (NeurIPS 2024 · similarity 0.85)
- K-ON: Stacking Knowledge on the Head Layer of Large Language Model (AAAI 2025 · similarity 0.85)
- KGDM: A Diffusion Model to Capture Multiple Relation Semantics for Knowledge Graph Embedding (AAAI 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.
