Reinforcement Learning for Abstractive Question Summarization with Question-aware Semantic Rewards

TL;DR

This paper presents a reinforcement learning framework for abstractive question summarization that uses question-aware semantic rewards to improve relevance and factual accuracy, especially in medical questions.

Contribution

It introduces novel reward functions based on question-type and focus recognition to enhance question summarization quality.

Findings

Outperforms state-of-the-art models on benchmark datasets.

Generated summaries are more diverse and factually consistent.

Reinforcement learning with semantic rewards improves summarization accuracy.

Abstract

The growth of online consumer health questions has led to the necessity for reliable and accurate question answering systems. A recent study showed that manual summarization of consumer health questions brings significant improvement in retrieving relevant answers. However, the automatic summarization of long questions is a challenging task due to the lack of training data and the complexity of the related subtasks, such as the question focus and type recognition. In this paper, we introduce a reinforcement learning-based framework for abstractive question summarization. We propose two novel rewards obtained from the downstream tasks of (i) question-type identification and (ii) question-focus recognition to regularize the question generation model. These rewards ensure the generation of semantically valid questions and encourage the inclusion of key medical entities/foci in the question summary. We evaluated our proposed method on two benchmark datasets and achieved higher performance over state-of-the-art models. The manual evaluation of the summaries reveals that the generated questions are more diverse and have fewer factual inconsistencies than the baseline summaries