Review-based Question Generation with Adaptive Instance Transfer and Augmentation
This addresses the inefficiency for consumers in extracting information from reviews, though it is incremental as it builds on existing neural generation methods.
The paper tackles the problem of generating questions from online reviews to help consumers find specific information, proposing an iterative learning framework with adaptive instance transfer and augmentation that achieves effective results across 10 product categories.
Online reviews provide rich information about products and service, while it remains inefficient for potential consumers to exploit the reviews for fulfilling their specific information need. We propose to explore question generation as a new way of exploiting review information. One major challenge of this task is the lack of review-question pairs for training a neural generation model. We propose an iterative learning framework for handling this challenge via adaptive transfer and augmentation of the training instances with the help of the available user-posed question-answer data. To capture the aspect characteristics in reviews, the augmentation and generation procedures incorporate related features extracted via unsupervised learning. Experiments on data from 10 categories of a popular E-commerce site demonstrate the effectiveness of the framework, as well as the usefulness of the new task.