Research map / Graph learning / Graph self-supervised learning
GraphER: Token-Centric Entity Resolution with Graph Convolutional Neural Networks
Bing Li, Wei Wang, Yifang Sun, Linhan Zhang, Muhammad Asif Ali, Yi Wang
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 ER-GCN structural embeddings (ablation) | GraphER · Amazon-Google | F1 (%): 56.91 -> 68.08 | Improved |
| add ER-GCN structural embeddings (ablation) | GraphER · BeerAdvo-RateBeer | F1 (%): 66.67 -> 79.71 | Improved |
| add cross-encoding (ablation) | GraphER · Amazon-Google | F1 (%): 25.67 -> 68.08 | Improved |
| add cross-encoding (ablation) | GraphER · BeerAdvo-RateBeer | F1 (%): 36.36 -> 79.71 | Improved |
| add token-gating (ablation) | GraphER · Amazon-Google | F1 (%): 66.52 -> 68.08 | Improved |
| add token-gating (ablation) | GraphER · BeerAdvo-RateBeer | F1 (%): 77.38 -> 79.71 | Improved |
| add pretrained GloVe embeddings (ablation) | GraphER · Amazon-Google | F1 (%): 67.11 -> 68.08 | Improved |
| add pretrained GloVe embeddings (ablation) | GraphER · BeerAdvo-RateBeer | F1 (%): 77.53 -> 79.71 | Improved |
| use token-centric instead of attribute-centric comparison (ablation) | GraphER comparison layer · Amazon-Google | F1 (%): 47.87 -> 68.08 | Improved |
| use token-centric instead of record-centric comparison (ablation) | GraphER comparison layer · BeerAdvo-RateBeer | F1 (%): 57.27 -> 79.71 | Improved |
| stack more than 2 GCN layers (ablation) | ER-GCN · Amazon-Google and BeerAdvo-RateBeer dev | F1 | Hurt |
| replace attribute-centric DL models (RNN/Hybrid) with GraphER | ER models · Amazon-Google | F1 (%): 60.51 -> 68.08 | Improved |
Closest papers by meaning
- Revisit and Outstrip Entity Alignment: A Perspective of Generative Models (ICLR 2024 · similarity 0.85)
- Multipartite Entity Resolution: Motivating a K-Tuple Perspective (Student Abstract) (AAAI 2024 · similarity 0.84)
- Select and Augment: Enhanced Dense Retrieval Knowledge Graph Augmentation (Abstract Reprint) (AAAI 2024 · similarity 0.84)
- Lambda: Learning Matchable Prior For Entity Alignment with Unlabeled Dangling Cases (NeurIPS 2024 · similarity 0.84)
- Entity Alignment with Noisy Annotations from Large Language Models (NeurIPS 2024 · similarity 0.84)
- Span Graph Transformer for Document-Level Named Entity Recognition (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.
