# Review-based Question Generation with Adaptive Instance Transfer and Augmentation

arXiv: https://arxiv.org/abs/1911.01556 · HTML: https://mlsanity.com/paper/1911.01556/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Nov 2019.

## Built on by (most cited first, 8 of 8)

- [SANCL: Multimodal Review Helpfulness Prediction with Selective Attention and Natural Contrastive Learning](https://mlsanity.com/paper/2209.05040/) (2022)
- [QRelScore: Better Evaluating Generated Questions with Deeper Understanding of Context-aware Relevance](https://mlsanity.com/paper/2204.13921/) (2022)
- [Evaluation of Question Generation Needs More References](https://mlsanity.com/paper/2305.16626/) (2023)
- [Generating Self-Contained and Summary-Centric Question Answer Pairs via Differentiable Reward Imitation Learning](https://mlsanity.com/paper/2109.04689/) (2021)
- [Unified Question Generation with Continual Lifelong Learning](https://mlsanity.com/paper/2201.09696/) (2022)
- [Ask To The Point: Open-Domain Entity-Centric Question Generation](https://mlsanity.com/paper/2310.14126/) (2023)
- [Certifying Knowledge Comprehension in LLMs](https://mlsanity.com/paper/2402.15929/) (2024)
- [Learning to Diversify for Product Question Generation](https://mlsanity.com/paper/2207.02534/) (2022)

## Abstract (arXiv)

Online reviews provide rich information about products and service, while it remains inefficient for potential consumers to exploit the reviews for fulfilling their specific information need. We propose to explore question generation as a new way of exploiting review information. One major challenge of this task is the lack of review-question pairs for training a neural generation model. We propose an iterative learning framework for handling this challenge via adaptive transfer and augmentation of the training instances with the help of the available user-posed question-answer data. To capture the aspect characteristics in reviews, the augmentation and generation procedures incorporate related features extracted via unsupervised learning. Experiments on data from 10 categories of a popular E-commerce site demonstrate the effectiveness of the framework, as well as the usefulness of the new task.