Research map / Label-efficient and robust learning / Recognition and long-tail
Mining Entity Synonyms with Efficient Neural Set Generation
Jiaming Shen, Ruiliang Lyu, Xiang Ren, Michelle Vanni, Brian Sadler, Jiawei Han
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 holistic set-instance scoring rather than the strongest reported baseline | SynSetMine · Wiki | ARI: 44.78 ($\pm$0.28) -> 56.43 ($\pm$1.31) | Improved |
| use holistic set-instance scoring rather than the strongest reported baseline | SynSetMine · NYT | ARI: 43.92 ($\pm$0.90) -> 44.91 ($\pm$2.16) | Improved |
| use holistic set-instance scoring rather than the strongest reported baseline | SynSetMine · PubMed | ARI: 58.91 ($\pm$0.08) -> 74.33 ($\pm$0.66) | Improved |
| add the Embedding Transformer (ablation) | SynSetMine set scorer · Wiki | ARI: 46.48 -> 56.43 | Improved |
| add the Embedding Transformer (ablation) | SynSetMine set scorer · NYT | ARI: 39.86 -> 44.91 | Improved |
| add the Post Transformer (ablation) | SynSetMine set scorer · Wiki | ARI: 1.50 -> 56.43 | Improved |
| add the Post Transformer (ablation) | SynSetMine set scorer · NYT | ARI: 0.82 -> 44.91 | Improved |
| use Both-250-500 hidden layer sizes instead of Both-100-200 (ablation) | SynSetMine set scorer · Wiki | ARI: 49.38 -> 57.34 | Improved |
| use Both-250-500 hidden layer sizes instead of Both-100-200 (ablation) | SynSetMine set scorer · NYT | ARI: 37.64 -> 48.89 | Improved |
| use Both-300-600 hidden layer sizes instead of Both-250-500 (ablation) | SynSetMine set scorer · Wiki | ARI: 57.34 -> 56.26 | Hurt |
| use Both-300-600 hidden layer sizes instead of Both-250-500 (ablation) | SynSetMine set scorer · NYT | ARI: 48.89 -> 46.65 | Hurt |
| use mixed negative sampling instead of share-token sampling (ablation) | SynSetMine training pairs · Wiki | clustering performance | Improved |
Closest papers by meaning
- A Recurrent Model for Collective Entity Linking with Adaptive Features (AAAI 2020 · similarity 0.83)
- A Generative Model of Words and Relationships from Multiple Sources (AAAI 2016 · similarity 0.82)
- Antonym-Synonym Classification Based on New Sub-Space Embeddings (AAAI 2019 · similarity 0.82)
- Seed-Guided Fine-Grained Entity Typing in Science and Engineering Domains (AAAI 2024 · similarity 0.81)
- UniversalNER: Targeted Distillation from Large Language Models for Open Named Entity Recognition (ICLR 2024 · similarity 0.80)
- Multi-Grained Query-Guided Set Prediction Network for Grounded Multimodal Named Entity Recognition (AAAI 2025 · similarity 0.80)
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.
