Diverse and Specific Clarification Question Generation with Keywords

TL;DR

This paper introduces KPCNet, a novel model for generating diverse and specific clarification questions in e-commerce, addressing the limitations of previous methods by focusing on diversity and topic specificity.

Contribution

The paper proposes the task of Diverse Clarification Question Generation and introduces KPCNet, a model that improves question specificity and diversity using keyword prediction and conditioning.

Findings

KPCNet generates more specific questions than baselines.

KPCNet achieves higher diversity in question generation.

Human and automatic evaluations confirm the effectiveness of KPCNet.

Abstract

Product descriptions on e-commerce websites often suffer from missing important aspects. Clarification question generation (CQGen) can be a promising approach to help alleviate the problem. Unlike traditional QGen assuming the existence of answers in the context and generating questions accordingly, CQGen mimics user behaviors of asking for unstated information. The generated CQs can serve as a sanity check or proofreading to help e-commerce merchant to identify potential missing information before advertising their product, and improve consumer experience consequently. Due to the variety of possible user backgrounds and use cases, the information need can be quite diverse but also specific to a detailed topic, while previous works assume generating one CQ per context and the results tend to be generic. We thus propose the task of Diverse CQGen and also tackle the challenge of specificity. We propose a new model named KPCNet, which generates CQs with Keyword Prediction and Conditioning, to deal with the tasks. Automatic and human evaluation on 2 datasets (Home & Kitchen, Office) showed that KPCNet can generate more specific questions and promote better group-level diversity than several competing baselines.