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.