Research map / Large language models / Retrieval and knowledge
Improving Neural Question Generation Using Answer Separation
Yanghoon Kim, Hwanhee Lee, Joongbo Shin, Kyomin Jung
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 |
|---|---|---|---|
| Separate passage and answer information and replace the answer span with a special token (ablation) | ASs2s · SQuAD Split-1 | BLEU-4: 14.37 $\pm$ 0.28 -> 16.20 $\pm$ 0.32 | Improved |
| Add keyword-net to extract key information from the target answer (ablation) | ASs2s · SQuAD Split-1 | BLEU-4: 13.95 $\pm$ 0.29 -> 16.20 $\pm$ 0.32 | Improved |
| Use the answer-separated decoder rather than a general LSTM decoder (ablation) | ASs2s · SQuAD Split-1 | BLEU-4: 12.30 $\pm$ 0.26 -> 16.20 $\pm$ 0.32 | Improved |
| Use answer-separated seq2seq instead of seq2seq+AP | SQuAD question generation · Generated questions | Complete target-answer inclusion: 0.8\% -> 0.6\% | Improved |
| Use answer-separated seq2seq instead of seq2seq+AP | SQuAD question generation · Generated questions | Partial target-answer inclusion: 17.3\% -> 9.5\% | Improved |
| Replace answer-position features with answer separation | Question-type prediction · SQuAD | Recall: 77.3\% -> 82.0\% (what); 56.2\% -> 74.1\% (how); 19.4\% -> 43.3\% (when); 3.4\% -> 6.1\% (which); 12.1\% -> 46.3\% (wher | Improved |
Closest papers by meaning
- Neural Question Generation with Answer Pivot (AAAI 2020 · similarity 0.91)
- Improving Question Generation with Sentence-Level Semantic Matching and Answer Position Inferring (AAAI 2020 · similarity 0.89)
- Reinforcement Learning Based Graph-to-Sequence Model for Natural Question Generation (ICLR 2020 · similarity 0.87)
- Generative Question Answering: Learning to Answer the Whole Question (ICLR 2019 · similarity 0.87)
- Improving Knowledge-Aware Dialogue Generation via Knowledge Base Question Answering (AAAI 2020 · similarity 0.86)
- UniGen: A Unified Generative Framework for Retrieval and Question Answering with Large Language Models (AAAI 2024 · similarity 0.84)
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.
