E-commerce Query-based Generation based on User Review
This addresses a specific efficiency issue for e-commerce shoppers, but the approach is incremental as it builds on existing seq2seq methods with added attention and conditioning mechanisms.
The paper tackles the problem of users spending excessive time browsing irrelevant product reviews on e-commerce platforms by proposing a seq2seq model that generates answers to user questions based on reviews, achieving improved performance in experiments.
With the increasing number of merchandise on e-commerce platforms, users tend to refer to reviews of other shoppers to decide which product they should buy. However, with so many reviews of a product, users often have to spend lots of time browsing through reviews talking about product attributes they do not care about. We want to establish a system that can automatically summarize and answer user's product specific questions. In this study, we propose a novel seq2seq based text generation model to generate answers to user's question based on reviews posted by previous users. Given a user question and/or target sentiment polarity, we extract aspects of interest and generate an answer that summarizes previous relevant user reviews. Specifically, our model performs attention between input reviews and target aspects during encoding and is conditioned on both review rating and input context during decoding. We also incorporate a pre-trained auxiliary rating classifier to improve model performance and accelerate convergence during training. Experiments using real-world e-commerce dataset show that our model achieves improvement in performance compared to previously introduced models.