Research map / Large language models / Language, safety and interpretability
Cross-Lingual Entity Linking for Web Tables
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 coherence feature to mention+context features (ablation) | Joint table linker · Validation set | Micro Acc.: 0.652 -> 0.692 | Helped |
| add context feature to mention feature (mention only vs full) (ablation) | Joint table linker · Validation set | Micro Acc.: 0.604 -> 0.692 | Helped |
| use coherence feature alone (ablation) | Joint table linker · Validation set | Micro Acc.: 0.692 -> 0.279 | Hurt |
| add pre-training step (ablation) | Ours (Full) · Cross-lingual table linking | Micro Acc.: 0.606 -> 0.629 | Helped |
| use multiple translation tools instead of Baidu only (ablation) | Ours · Cross-lingual table linking | Micro Acc.: 0.576 -> 0.606 | Helped |
| use RankNet loss instead of hinge loss in joint model (ablation) | Joint model, no coherence · Cross-lingual table linking | Micro Acc.: 0.574 -> 0.598 | Helped |
| go from non-joint to joint with hinge loss (ablation) | Table linker, no coherence · Cross-lingual table linking | Micro Acc.: 0.586 -> 0.574 | Hurt |
| add coherence (joint scoring) with RankNet (ablation) | Joint model · Cross-lingual table linking | Micro Acc.: 0.598 -> 0.629 | Helped |
| joint neural model vs TabEL_W in mono-lingual Chinese | Table linker · Chinese mono-lingual table linking | Micro Acc.: 0.852 -> 0.886 | Helped |
| ensemble all translation resources instead of Baidu | Candidate generation · Chinese mentions | Hits@1: 0.542 -> 0.558 | Helped |
Closest papers by meaning
- Neural Cross-Lingual Entity Linking (AAAI 2018 · similarity 0.89)
- MCL-NER: Cross-Lingual Named Entity Recognition via Multi-View Contrastive Learning (AAAI 2024 · similarity 0.86)
- Knowledge Graph Completion with Relation-Aware Anchor Enhancement (AAAI 2025 · similarity 0.84)
- Three Heads Are Better than One: Improving Cross-Domain NER with Progressive Decomposed Network (AAAI 2024 · similarity 0.84)
- HLMEA: Unsupervised Entity Alignment Based on Hybrid Language Models (AAAI 2025 · similarity 0.84)
- Entity Alignment with Noisy Annotations from Large Language Models (NeurIPS 2024 · similarity 0.83)
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.