Research map / Continual learning / Online and replay-based
TempEL: Linking Dynamically Evolving and Newly Emerging Entities
Klim Zaporojets, Lucie-Aimée Kaffee, Johannes Deleu, Thomas Demeester, Chris Develder, Isabelle Augenstein
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 |
|---|---|---|---|
| test on 2022 instead of 2013 snapshot (model finetuned on 2013) | BLINK bi-encoder · TempEL continual entities | Accuracy@64: 0.785 -> 0.750 | Hurt |
| finetune on 2022 snapshot instead of 2013, test on 2013 | BLINK bi-encoder · TempEL continual entities, test 2013 | Accuracy@64: 0.785 -> 0.790 | Improved |
| finetune on 2021 snapshot instead of 2013, test on 2013 | BLINK bi-encoder · TempEL new entities, test 2013 | Accuracy@64: 0.910 -> 0.910 | No clear effect |
| test on 2021 snapshot instead of 2013 (finetuned 2013) | BLINK bi-encoder · TempEL new entities | Accuracy@64: 0.910 -> 0.688 | Hurt |
| finetune on 2021 and test on 2021 vs finetune on 2013 test on 2021 | BLINK bi-encoder · TempEL new entities, test 2021 | Accuracy@64: 0.688 -> 0.761 | Improved |
| finetune in-snapshot for continual entities (2022) | BLINK bi-encoder · TempEL continual entities, test 2022 | Accuracy@64: 0.750 -> 0.760 | Improved |
| finetune in-snapshot for continual entities (2016) | BLINK bi-encoder · TempEL continual entities, test 2016 | Accuracy@64: 0.772 -> 0.777 | Improved |
| increase temporal distance between finetune and test snapshot | BLINK bi-encoder · TempEL | Accuracy@64 | Hurt |
| finetune on future snapshots, test on past (positive temporal offset) | BLINK bi-encoder · TempEL continual entities | Accuracy@64 | Improved |
Closest papers by meaning
- EMERGE: A Benchmark for Updating Knowledge Graphs with Emerging Textual Knowledge (NeurIPS 2026 · similarity 0.86)
- TGB 2.0: A Benchmark for Learning on Temporal Knowledge Graphs and Heterogeneous Graphs (NeurIPS 2024 · similarity 0.85)
- ChroKnowledge: Unveiling Chronological Knowledge of Language Models in Multiple Domains (ICLR 2025 · similarity 0.84)
- Physics of Language Models: Part 3.1, Knowledge Storage and Extraction (ICML 2024 · similarity 0.83)
- Revisiting Document-Level Relation Extraction with Context-Guided Link Prediction (AAAI 2024 · similarity 0.83)
- HLMEA: Unsupervised Entity Alignment Based on Hybrid Language Models (AAAI 2025 · 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.
