Answer Identification from Product Reviews for User Questions by Multi-Task Attentive Networks

• DOI: 10.1609/aaai.v33i01.330145
• Publication Date: 2019-09-13T21:56:35Z
• Authors: Long Chen; Ziyu Guan; Wei Zhao; Wanqing Zhao; Xiaopeng Wang; Zhou Zhao; Huan Sun
• Keywords: Identification; Similarity (geometry)

Online Shopping has become a part of our daily routine, but it still cannot offer intuitive experience as store shopping. Nowadays, most e-commerce Websites Question Answering (QA) system that allows users to consult other who have purchased the product. However, need wait patiently for others’ replies. In this paper, we investigate how provide quick response asker by plausible answer identification from product reviews. By analyzing similarity and discrepancy between explicit answers reviews can be answers, novel multi-task deep learning method with carefully designed attention mechanisms is developed. The well exploit large amounts user generated QA data few manually labeled review address problem. Experiments on collected Amazon demonstrate its effectiveness superiority over competitive baselines.