Research map / Large language models / Language, safety and interpretability
Content and Context: Two-Pronged Bootstrapped Learning for Regex-Formatted Entity Extraction
Stanley Simoes, Deepak P, Munu Sairamesh, Deepak Khemani, Sameep Mehta
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 |
|---|---|---|---|
| Content plus context logistic regression instead of GM10 (Gupta and Manning) | match set expansion · DATEMIDEAST | F-score: 0.016 -> 0.513 | Improved |
| OURS instead of GM1% | match set expansion · DATEWEBKB | F-score: 0.391 -> 0.923 | Improved |
| OURS instead of GM1% | match set expansion · COURSEWEBKB | F-score: 0.450 -> 0.919 | Improved |
| OURS instead of GM1% | match set expansion · PHONEFORSALE | F-score: 0.324 -> 0.648 | Improved |
| OURS instead of GM10 | match set expansion · DATEENRON | F-score: 0.759 -> 0.900 | Improved |
| OURS instead of M(rseed, D) seed matches only | match set expansion · PHONEENRON | F-score: 0.812 -> 0.796 | Hurt |
| Increase generalization depth d to 4 | OURS · COURSEWEBKB | F-score | Improved |
| Vary generalization depth d | OURS · other tasks | F-score | No clear effect |
| Increase number of iterations num beyond 150-300 | OURS · all tasks | F-score | Hurt |
| Expansion rate p above 2% (0.5% to 7.5%) | OURS · COURSEWEBKB | F-score | Hurt |
Closest papers by meaning
- UniversalNER: Targeted Distillation from Large Language Models for Open Named Entity Recognition (ICLR 2024 · similarity 0.82)
- Small Language Model Makes an Effective Long Text Extractor (AAAI 2025 · similarity 0.82)
- DocKS-RAG: Optimizing Document-Level Relation Extraction through LLM-Enhanced Hybrid Prompt Tuning (ICML 2025 · similarity 0.82)
- Retrieval is Accurate Generation (ICLR 2024 · similarity 0.81)
- RoPDA: Robust Prompt-Based Data Augmentation for Low-Resource Named Entity Recognition (AAAI 2024 · similarity 0.81)
- An Autoregressive Text-to-Graph Framework for Joint Entity and Relation Extraction (AAAI 2024 · similarity 0.81)
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.
