Research map / Label-efficient and robust learning / Recognition and long-tail
Knowledge-aware Named Entity Recognition with Alleviating Heterogeneity
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| incorporate type-heterogeneous KB knowledge with KaNa | NER models on MIT-Movie · MIT-Movie | F1: 74.62•±0.20 -> 76.38±0.06 | Helped |
| incorporate type-heterogeneous KB knowledge with KaNa | NER models on RE3D · RE3D | F1: 68.81•±0.18 -> 69.29±0.12 | Helped |
| incorporate type-heterogeneous KB knowledge with KaNa | NER models on MIT-Restaurant · MIT-Restaurant | F1: 79.60•±0.23 -> 80.43±0.19 | Helped |
| incorporate type-heterogeneous KB knowledge with KaNa | NER models on BC5CDR-Disease · BC5CDR-Disease | F1: 85.16•±0.27 -> 86.13±0.12 | Helped |
| incorporate type-heterogeneous KB knowledge with KaNa | NER models on AnEM · AnEM | F1: 62.93•±0.29 -> 63.41±0.09 | Helped |
| add the knowledge denoising module (ablation) | KaNa · MIT-Movie | F1: 74.64 -> 76.38 | Helped |
| initialize entity nodes with PBG rather than Entity-Glove embeddings (ablation) | KaNa · MIT-Movie | F1: 76.38 -> 75.68 | Hurt |
| add one-hop relational knowledge to the text-entity graph (ablation) | KaNa · MIT-Movie | F1: 76.38 -> 75.56 | Hurt |
Closest papers by meaning
- ConsistNER: Towards Instructive NER Demonstrations for LLMs with the Consistency of Ontology and Context (AAAI 2024 · similarity 0.89)
- Three Heads Are Better than One: Improving Cross-Domain NER with Progressive Decomposed Network (AAAI 2024 · similarity 0.88)
- UniversalNER: Targeted Distillation from Large Language Models for Open Named Entity Recognition (ICLR 2024 · similarity 0.88)
- MCL-NER: Cross-Lingual Named Entity Recognition via Multi-View Contrastive Learning (AAAI 2024 · similarity 0.88)
- A Reasoning Paradigm for Named Entity Recognition (AAAI 2026 · similarity 0.88)
- GuideNER: Annotation Guidelines Are Better than Examples for In-Context Named Entity Recognition (AAAI 2025 · similarity 0.87)
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.