# Improving Question Generation with Sentence-level Semantic Matching and Answer Position Inferring

arXiv: https://arxiv.org/abs/1912.00879 · HTML: https://mlsanity.com/paper/1912.00879/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Dec 2019.

## Built on by (most cited first, 11 of 11)

- [Improving Unsupervised Question Answering via Summarization-Informed Question Generation](https://mlsanity.com/paper/2109.07954/) (2021)
- [Question Generation for Reading Comprehension Assessment by Modeling How and What to Ask](https://mlsanity.com/paper/2204.02908/) (2022)
- [MinPrompt: Graph-based Minimal Prompt Data Augmentation for Few-shot Question Answering](https://mlsanity.com/paper/2310.05007/) (2023)
- [QAScore -- An Unsupervised Unreferenced Metric for the Question Generation Evaluation](https://mlsanity.com/paper/2210.04320/) (2022)
- [Survey of Natural Language Processing for Education: Taxonomy, Systematic Review, and Future Trends](https://mlsanity.com/paper/2401.07518/) (2024)
- [Unified Question Generation with Continual Lifelong Learning](https://mlsanity.com/paper/2201.09696/) (2022)
- [Consecutive Question Generation via Dynamic Multitask Learning](https://mlsanity.com/paper/2211.08850/) (2022)
- [Enhancing Pre-trained Models with Text Structure Knowledge for Question Generation](https://mlsanity.com/paper/2209.04179/) (2022)
- [Automating Turkish Educational Quiz Generation Using Large Language Models](https://mlsanity.com/paper/2406.03397/) (2024)
- [Regularizing Differentiable Architecture Search with Smooth Activation](https://mlsanity.com/paper/2504.16306/) (2025)
- [Exploring Answer Information Methods for Question Generation with Transformers](https://mlsanity.com/paper/2312.03483/) (2023)

## Abstract (arXiv)

Taking an answer and its context as input, sequence-to-sequence models have made considerable progress on question generation. However, we observe that these approaches often generate wrong question words or keywords and copy answer-irrelevant words from the input. We believe that lacking global question semantics and exploiting answer position-awareness not well are the key root causes. In this paper, we propose a neural question generation model with two concrete modules: sentence-level semantic matching and answer position inferring. Further, we enhance the initial state of the decoder by leveraging the answer-aware gated fusion mechanism. Experimental results demonstrate that our model outperforms the state-of-the-art (SOTA) models on SQuAD and MARCO datasets. Owing to its generality, our work also improves the existing models significantly.