Research map / Label-efficient and robust learning / Recognition and long-tail
Incorporating Expert Knowledge into Keyphrase Extraction
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 Set-1 labeled features (CeKE/Maui predictions) via posterior regularization (ablation) | CRF tagger · KDD | F1: 0.2823 -> 0.3407 | Helped |
| add Set-1 labeled features via posterior regularization (ablation) | CRF tagger · WWW | F1: 0.2547 -> 0.3049 | Helped |
| add Set-1 labeled features via posterior regularization (ablation) | CRF tagger · WWW | recall: 0.1945 -> 0.3558 | Helped |
| add automatically extracted PMI labeled features via PR (ablation) | CRF tagger · KDD | F1: 0.2823 -> 0.3085∗ | Helped |
| add automatically extracted frequency labeled features via PR (ablation) | CRF tagger · WWW | F1: 0.2547 -> 0.2717 | Helped |
| token-level CRF sequence tagging instead of phrase classifier (Kea) | keyphrase extraction · KDD | F1: 0.2105 -> 0.2823 | Helped |
| token-level CRF sequence tagging instead of phrase classifiers (CeKE, Maui) | keyphrase extraction · WWW | F1: 0.2504 -> 0.2547 | No clear effect |
| add CeKE/Maui predictions as regular CRF features instead of PR (ablation) | CRF tagger · WWW | F1 | No clear effect |
| add neighborhood features to unigram features (ablation) | CRF tagger · WWW | F1 | Helped |
| add title features (ablation) | CRF tagger · WWW | F1 | Helped |
Closest papers by meaning
- Unsupervised Deep Keyphrase Generation (AAAI 2022 · similarity 0.86)
- KGGen: Extracting Knowledge Graphs from Plain Text with Language Models (NeurIPS 2025 · similarity 0.83)
- Unsupervised Extractive Summarization with Learnable Length Control Strategies (AAAI 2024 · similarity 0.82)
- Learning Pattern-Based Extractors from Natural Language and Knowledge Graphs: Applying Large Language Models to Wikipedia and Linked Open Data (AAAI 2024 · similarity 0.81)
- Seed-Guided Fine-Grained Entity Typing in Science and Engineering Domains (AAAI 2024 · similarity 0.81)
- DocKS-RAG: Optimizing Document-Level Relation Extraction through LLM-Enhanced Hybrid Prompt Tuning (ICML 2025 · 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.