Research map / Large language models / Retrieval and knowledge
The Value of Paraphrase for Knowledge Base Predicates
Bingcong Xue, Sen Hu, Lei Zou, Jiashu Cheng
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 |
|---|---|---|---|
| replace Patty with new paraphrase dictionary | gAnswer · QALD6-test | recall: 0.170 -> 0.260 | Improved |
| replace Patty with new paraphrase dictionary | gAnswer · QALD6-train | recall: 0.303 -> 0.331 | Improved |
| replace Patty with new paraphrase dictionary | gAnswer · QALD7-train | recall: 0.349 -> 0.409 | Improved |
| replace Patty with new paraphrase dictionary | gAnswer · QALD6-test | precision: 0.395 -> 0.553 | Improved |
| replace Patty with new paraphrase dictionary | gAnswer · QALD8-test | precision: 0.667 -> 0.733 | Improved |
| replace Patty with new paraphrase dictionary | gAnswer · QALD7-test | right (correct answers): 11 -> 12 | Improved |
| replace Patty with new paraphrase dictionary | gAnswer · QALD6-test | right (correct answers): 17 -> 26 | Improved |
| replace Patty with new paraphrase dictionary | gAnswer · QALD7-train | questions with better SPARQLs: 32 | Improved |
| replace Patty with new paraphrase dictionary | gAnswer · QALD7-train | questions with worse SPARQLs than Patty | No clear effect |
| replace Patty with new paraphrase dictionary | gAnswer · QALD8-test | recall: 0.244 -> 0.268 | Improved |
| add paraphrase dictionary at end of pointer-generator | pointer-generator · QALD question generation | distinct-1: 0.499 -> 0.504 | Improved |
| add paraphrase dictionary at end of pointer-generator | pointer-generator · QALD question generation | distinct-2: 0.811 -> 0.815 | Improved |
Closest papers by meaning
- Integrating Linguistic Knowledge to Sentence Paraphrase Generation (AAAI 2020 · similarity 0.87)
- Idiomatic Expression Paraphrasing without Strong Supervision (AAAI 2022 · similarity 0.85)
- Semantic-KG: Using Knowledge Graphs to Construct Benchmarks for Measuring Semantic Similarity (NeurIPS 2025 · similarity 0.81)
- KGGen: Extracting Knowledge Graphs from Plain Text with Language Models (NeurIPS 2025 · similarity 0.81)
- LAMPAT: Low-Rank Adaption for Multilingual Paraphrasing Using Adversarial Training (AAAI 2024 · similarity 0.80)
- Well-Written Knowledge Graphs: Most Effective RDF Syntaxes for Triple Linearization in End-to-End Extraction of Relations from Texts (Student Abstract) (AAAI 2024 · similarity 0.80)
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.
