Research map / Label-efficient and robust learning / Recognition and long-tail
Prototypical Representation Learning for Relation Extraction
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 |
|---|---|---|---|
| Use collaboratively trained prototypes with statement and prototype metrics plus prototype-level classification | BERT-base relation encoder · FewRel 5-way 1-shot | accuracy (%): 91.02 -> 92.51 | Helped |
| Use collaboratively trained prototypes with statement and prototype metrics plus prototype-level classification | BERT-base relation encoder · FewRel 10-way 1-shot | accuracy (%): 84.95 -> 86.39 | Helped |
| Use collaboratively trained prototypes | MTB relation encoder · FuzzyRED 1-shot | accuracy (%): 51.3 -> 53.2 | Helped |
| Use collaboratively trained prototypes | MTB relation encoder · SemEval 2010 Task 8 | F-measure: 87.7 -> 88.0 | Helped |
| Add prototype-level classification loss (ablation) | COL with prototype metrics · FewRel 5-way 1-shot | accuracy (%): 90.40 -> 91.12 | Helped |
| Add the statement-statement metric loss (ablation) | COL with prototype losses and classification · FewRel 5-way 1-shot | accuracy (%): 91.12 -> 92.51 | Helped |
| Use L_S2S instead of L_S2S' (ablation) | COL with prototype losses and classification · FewRel 5-way 1-shot | accuracy (%): 91.08 -> 92.51 | Helped |
| Use learned collaborative prototypes instead of fixed rule-based prototypes | IND relation encoder · FewRel 5-way 1-shot | accuracy (%): 89.90 -> 92.51 | Helped |
Closest papers by meaning
- Distant Supervision via Prototype-Based Global Representation Learning (AAAI 2017 · similarity 0.90)
- SEE: Syntax-Aware Entity Embedding for Neural Relation Extraction (AAAI 2018 · similarity 0.89)
- Prototype-Guided Multimodal Relation Extraction based on Entity Attributes (AAAI 2025 · similarity 0.88)
- Global Distant Supervision for Relation Extraction (AAAI 2016 · similarity 0.88)
- Synergistic Anchored Contrastive Pre-training for Few-Shot Relation Extraction (AAAI 2024 · similarity 0.87)
- Few-Shot, No Problem: Descriptive Continual Relation Extraction (AAAI 2025 · similarity 0.86)
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.