arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2104.10317cs.CLcs.AI
收藏

使用关键词生成多样和特定的澄清问题

Diverse and Specific Clarification Question Generation with Keywords

Shanghai Jiao Tong University(上海交通大学)

Zhiling Zhang, Kenny Q. Zhu

摘要:

电子商务网站上的产品描述往往缺少重要方面。澄清问题生成(CQGen)可以是一种很有前途的方法,以帮助缓解问题。与传统的QGen假设上下文中存在答案并相应地生成问题不同,CQGen模仿用户询问未陈述信息的行为。所生成的CQ可以用作健全性检查或校对,以帮助电子商务商家在广告他们的产品之前识别潜在的缺失信息,并因此改善消费者体验。由于可能的用户背景和用例的多样性,信息需求可以是相当多样化的,但也具体到一个详细的主题,而以前的工作假设每个上下文生成一个CQ,结果往往是通用的。因此,我们提出了多样化CQGen的任务,并解决了特异性的挑战。我们提出了一个新的模型命名为KPCNet,它产生的关键字预测和条件,处理任务的CQ。对2个数据集(家庭和厨房,办公室)的自动和人工评估表明,KPCNet可以生成更具体的问题,并促进比几个竞争基线更好的群体层次的多样性。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑