Research map / Label-efficient and robust learning / Recognition and long-tail
Cross-Relation Cross-Bag Attention for Distantly-Supervised 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 |
|---|---|---|---|
| add cross-relation attention instead of vanilla selective attention (ablation) | PCNN relation extractor · NYT sentence-level relation extraction | F1: 0.377 -> 0.411 | Helped |
| add cross-relation attention instead of vanilla selective attention (ablation) | BLSTM relation extractor · NYT sentence-level relation extraction | F1: 0.382 -> 0.409 | Helped |
| add cross-bag attention to cross-relation attention (ablation) | PCNN relation extractor · NYT sentence-level relation extraction | F1: 0.411 -> 0.421 | Helped |
| add cross-bag attention to cross-relation attention (ablation) | BLSTM relation extractor · NYT sentence-level relation extraction | F1: 0.409 -> 0.448 | Helped |
| replace cosine similarity with dot product for attention scoring (ablation) | PCNN+C²SA · NYT sentence-level relation extraction | F1: 0.421 -> 0.400 | Hurt |
| replace cosine similarity with dot product for attention scoring (ablation) | BLSTM+C²SA · NYT sentence-level relation extraction | F1: 0.448 -> 0.401 | Hurt |
| use C²SA rather than vanilla selective attention | PCNN and BLSTM relation extractors · NYT corpus-level relation extraction | Precision-recall performance | Helped |
| combine sentence bags with cross-bag attention (ablation) | C²SA relation extractor · NYT corpus-level relation extraction | Precision-recall performance | Helped |
Closest papers by meaning
- Self-Attention Enhanced Selective Gate with Entity-Aware Embedding for Distantly Supervised Relation Extraction (AAAI 2020 · similarity 0.91)
- Distant Supervision for Relation Extraction with Sentence-Level Attention and Entity Descriptions (AAAI 2017 · similarity 0.88)
- Are Noisy Sentences Useless for Distant Supervised Relation Extraction? (AAAI 2020 · similarity 0.88)
- Improving Distantly Supervised Relation Extraction with Neural Noise Converter and Conditional Optimal Selector (AAAI 2019 · similarity 0.87)
- Enhancing Low-Resource Relation Representations through Multi-View Decoupling (AAAI 2024 · similarity 0.84)
- A Positive-Unlabeled Metric Learning Framework for Document-Level Relation Extraction with Incomplete Labeling (AAAI 2024 · similarity 0.84)
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.