Question Answering Using Online Reviews

Review Reading Comprehension

Whenever we want to buy a product or use a service, we often have some questions about the product or service. If these questions can be answered immediately, it will help us make the purchase decision enormously. Thus, question-answering plays an important role in e-commerce. This work explores the potential of turning customer reviews into a large source of knowledge that can be used to answer user questions. We call this problem Review Reading Comprehension (RRC).

Given the ever-changing environment of products and services, it is very hard, if not impossible, to pre-compile an up-to-date and reliable knowledge base to cover a wide assortment of questions that customers may ask, such as in factoid based KB-QA. As a compromise, many online businesses leverage community question-answering (CQA) to crowdsource answers from existing customers. However, the problem with this approach is that many questions are not answered, and if they are answered, the answers are delayed, which is not suitable for interactive QA. In this work, we explore the potential of using product reviews as a large source of user experiences that can be exploited to obtain answers to user questions


Created on April 14, 2019 by Bing Liu.