Review-Driven Answer Generation for Product-Related Questions in E-Commerce

TL;DR

This paper introduces RAGE, a review-driven answer generation framework for E-commerce that efficiently extracts relevant review snippets and generates accurate, informative answers faster than existing models.

Contribution

The paper presents a novel multi-layer convolutional architecture for review-based answer generation, improving speed and accuracy over RNN-based models in E-commerce settings.

Findings

RAGE outperforms existing models in answer accuracy and informativeness.

RAGE significantly reduces training and generation time.

The framework effectively filters noise from reviews to guide answer creation.

Abstract

The users often have many product-related questions before they make a purchase decision in E-commerce. However, it is often time-consuming to examine each user review to identify the desired information. In this paper, we propose a novel review-driven framework for answer generation for product-related questions in E-commerce, named RAGE. We develope RAGE on the basis of the multi-layer convolutional architecture to facilitate speed-up of answer generation with the parallel computation. For each question, RAGE first extracts the relevant review snippets from the reviews of the corresponding product. Then, we devise a mechanism to identify the relevant information from the noise-prone review snippets and incorporate this information to guide the answer generation. The experiments on two real-world E-Commerce datasets show that the proposed RAGE significantly outperforms the existing alternatives in producing more accurate and informative answers in natural language. Moreover, RAGE takes much less time for both model training and answer generation than the existing RNN based generation models.