# Let's Ask Again: Refine Network for Automatic Question Generation

arXiv: https://arxiv.org/abs/1909.05355 · HTML: https://mlsanity.com/paper/1909.05355/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Aug 2019.

## Built on by (most cited first, 13 of 13)

- [ChatGPT Asks, BLIP-2 Answers: Automatic Questioning Towards Enriched Visual Descriptions](https://mlsanity.com/paper/2303.06594/) (2023)
- [All You May Need for VQA are Image Captions](https://mlsanity.com/paper/2205.01883/) (2022)
- [Conditional Generation Net for Medication Recommendation](https://mlsanity.com/paper/2202.06588/) (2022)
- [Quiz-Style Question Generation for News Stories](https://mlsanity.com/paper/2102.09094/) (2021)
- [GTM: A Generative Triple-Wise Model for Conversational Question Generation](https://mlsanity.com/paper/2106.03635/) (2021)
- [Learning to Ask Like a Physician](https://mlsanity.com/paper/2206.02696/) (2022)
- [Synthetic Question Value Estimation for Domain Adaptation of Question Answering](https://mlsanity.com/paper/2203.08926/) (2022)
- [FOLLOWUPQG: Towards Information-Seeking Follow-up Question Generation](https://mlsanity.com/paper/2309.05007/) (2023)
- [Automatic Comment Generation via Multi-Pass Deliberation](https://mlsanity.com/paper/2209.06634/) (2022)
- [Enhancing Question Generation with Commonsense Knowledge](https://mlsanity.com/paper/2106.10454/) (2021)
- [Enhancing Pre-trained Models with Text Structure Knowledge for Question Generation](https://mlsanity.com/paper/2209.04179/) (2022)
- [Inflected Forms Are Redundant in Question Generation Models](https://mlsanity.com/paper/2301.00397/) (2023)
- [idT5: Indonesian Version of Multilingual T5 Transformer](https://mlsanity.com/paper/2302.00856/) (2023)

## Abstract (arXiv)

In this work, we focus on the task of Automatic Question Generation (AQG) where given a passage and an answer the task is to generate the corresponding question. It is desired that the generated question should be (i) grammatically correct (ii) answerable from the passage and (iii) specific to the given answer. An analysis of existing AQG models shows that they produce questions which do not adhere to one or more of the above-mentioned qualities. In particular, the generated questions look like an incomplete draft of the desired question with a clear scope for refinement. To alleviate this shortcoming, we propose a method which tries to mimic the human process of generating questions by first creating an initial draft and then refining it. More specifically, we propose Refine Network (RefNet) which contains two decoders. The second decoder uses a dual attention network which pays attention to both (i) the original passage and (ii) the question (initial draft) generated by the first decoder. In effect, it refines the question generated by the first decoder, thereby making it more correct and complete. We evaluate RefNet on three datasets, textitviz., SQuAD, HOTPOT-QA, and DROP, and show that it outperforms existing state-of-the-art methods by 7-16% on all of these datasets. Lastly, we show that we can improve the quality of the second decoder on specific metrics, such as, fluency and answerability by explicitly rewarding revisions that improve on the corresponding metric during training. The code has been made publicly available footnotehttps://github.com/PrekshaNema25/RefNet-QG