Research map / Large language models / Retrieval and knowledge
Improving Question Generation with Sentence-Level Semantic Matching and Answer Position Inferring
Xiyao Ma, Qile Zhu, Yanlin Zhou, Xiaolin Li
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 |
|---|---|---|---|
| Combine sentence-level semantic matching and answer position inferring | Question generation model · SQuAD | BLEU-4: 15.82 -> 16.32 | Improved |
| Combine sentence-level semantic matching and answer position inferring | Question generation model · MS MARCO | BLEU-4: 17.95 -> 20.46 | Improved |
| Add sentence-level semantic matching (ablation) | Question generation model · SQuAD | BLEU-4: 15.66 -> 16.32 | Improved |
| Add answer position inferring (ablation) | Question generation model · SQuAD | BLEU-4: 15.77 -> 16.32 | Improved |
| Add sentence-level semantic matching (ablation) | Question generation model · MS MARCO | BLEU-4: 19.79 -> 20.46 | Improved |
| Add answer position inferring (ablation) | Question generation model · MS MARCO | BLEU-4: 20.14 -> 20.46 | Improved |
| Add sentence-level semantic matching | NQG++ · SQuAD | BLEU-4: 13.29 -> 14.97 | Improved |
| Add the proposed work | Pointer-generator · SQuAD | BLEU-4: 14.33 -> 16.32 | Improved |
| Add sentence-level semantic matching | Question generation model · SQuAD | Number of questions with right question words: 140 -> 150 | Improved |
| Add sentence-level semantic matching | Question generation model · SQuAD | Number of questions with right keywords: 148 -> 156 | Improved |
| Add answer position inferring | Question generation model · Copy precision | Precision: 47.21% -> 48.35% | Improved |
| Add answer position inferring | Question generation model · Copy recall | Recall: 38.38% -> 40.27% | Improved |
Closest papers by meaning
- Improving Neural Question Generation Using Answer Separation (AAAI 2019 · similarity 0.89)
- Capturing Greater Context for Question Generation (AAAI 2020 · similarity 0.89)
- Entity Guided Question Generation with Contextual Structure and Sequence Information Capturing (AAAI 2021 · similarity 0.89)
- UniGen: A Unified Generative Framework for Retrieval and Question Answering with Large Language Models (AAAI 2024 · similarity 0.86)
- Rethinking Generative Large Language Model Evaluation for Semantic Comprehension (ICML 2024 · similarity 0.86)
- The Consensus Game: Language Model Generation via Equilibrium Search (ICLR 2024 · similarity 0.86)
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.
