QQSUM: A Novel Task and Model of Quantitative Query-Focused Summarization for Review-based Product Question Answering

TL;DR

This paper introduces QQSUM, a new task and model for summarizing diverse customer opinions in product reviews to better answer user questions, using a novel approach that captures opinion diversity and quantifies their prevalence.

Contribution

The paper proposes QQSUM, a novel task for summarizing diverse opinions with quantification, and introduces QQSUM-RAG, a model that jointly retrieves and summarizes key points using few-shot learning.

Findings

QQSUM-RAG outperforms state-of-the-art RAG baselines in quality and quantification accuracy.

The model effectively captures diverse customer opinions in product reviews.

Experimental results validate the superiority of QQSUM-RAG over existing methods.

Abstract

Review-based Product Question Answering (PQA) allows e-commerce platforms to automatically address customer queries by leveraging insights from user reviews. However, existing PQA systems generate answers with only a single perspective, failing to capture the diversity of customer opinions. In this paper we introduce a novel task Quantitative Query-Focused Summarization (QQSUM), which aims to summarize diverse customer opinions into representative Key Points (KPs) and quantify their prevalence to effectively answer user queries. While Retrieval-Augmented Generation (RAG) shows promise for PQA, its generated answers still fall short of capturing the full diversity of viewpoints. To tackle this challenge, our model QQSUM-RAG, which extends RAG, employs few-shot learning to jointly train a KP-oriented retriever and a KP summary generator, enabling KP-based summaries that capture diverse and representative opinions. Experimental results demonstrate that QQSUM-RAG achieves superior performance compared to state-of-the-art RAG baselines in both textual quality and quantification accuracy of opinions. Our source code is available at: https://github.com/antangrocket1312/QQSUMM