# Generative Question Refinement with Deep Reinforcement Learning in Retrieval-based QA System

arXiv: https://arxiv.org/abs/1908.05604 · HTML: https://mlsanity.com/paper/1908.05604/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Aug 2019.

## Built on by (most cited first, 6 of 6)

- [Robust Training for Conversational Question Answering Models with Reinforced Reformulation Generation](https://mlsanity.com/paper/2310.13505/) (2023)
- [Attend, Memorize and Generate: Towards Faithful Table-to-Text Generation in Few Shots](https://mlsanity.com/paper/2203.00732/) (2022)
- [Answering Unanswered Questions through Semantic Reformulations in Spoken QA](https://mlsanity.com/paper/2305.17393/) (2023)
- [Increasing the Difficulty of Automatically Generated Questions via Reinforcement Learning with Synthetic Preference](https://mlsanity.com/paper/2410.08289/) (2024)
- [On the Robustness of Question Rewriting Systems to Questions of Varying Hardness](https://mlsanity.com/paper/2311.06807/) (2023)
- [Retrieval-Feedback-Driven Distillation and Preference Alignment for Efficient LLM-based Query Expansion](https://mlsanity.com/paper/2603.13776/) (2026)

## Abstract (arXiv)

In real-world question-answering (QA) systems, ill-formed questions, such as wrong words, ill word order, and noisy expressions, are common and may prevent the QA systems from understanding and answering them accurately. In order to eliminate the effect of ill-formed questions, we approach the question refinement task and propose a unified model, QREFINE, to refine the ill-formed questions to well-formed question. The basic idea is to learn a Seq2Seq model to generate a new question from the original one. To improve the quality and retrieval performance of the generated questions, we make two major improvements: 1) To better encode the semantics of ill-formed questions, we enrich the representation of questions with character embedding and the recent proposed contextual word embedding such as BERT, besides the traditional context-free word embeddings; 2) To make it capable to generate desired questions, we train the model with deep reinforcement learning techniques that considers an appropriate wording of the generation as an immediate reward and the correlation between generated question and answer as time-delayed long-term rewards. Experimental results on real-world datasets show that the proposed QREFINE method can generate refined questions with more readability but fewer mistakes than the original questions provided by users. Moreover, the refined questions also significantly improve the accuracy of answer retrieval.