FANDA:一种新的后续查询分析方法
FANDA: A Novel Approach to Perform Follow-up Query Analysis
摘要:
自然语言与数据库的接口(NLIDB)的研究引起了人们的广泛关注。NLIDB允许用户使用自然语言而不是类似SQL的查询语言来搜索数据库。在使用户不必学习查询语言的同时,与NLIDB的多轮交互通常涉及多个查询,其中上下文信息对于理解用户的查询意图至关重要。在本文中,我们解决了一个典型的上下文理解问题,称为后续查询分析。尽管其无处不在,后续查询分析没有得到很好的研究,由于两个主要障碍:后续查询场景的多样性和缺乏高质量的数据集。我们的工作总结了典型的后续查询场景,并提供了一个新的FollowUp数据集上的$1000$查询三元组120表。此外,我们提出了一种新的方法FANDA,它考虑到查询的结构,并采用弱监督最大边际学习的排名模型。FollowUp的实验结果证明了FANDA在多个指标上优于多个基线。
英文摘要:
Recent work on Natural Language Interfaces to Databases (NLIDB) has attracted considerable attention. NLIDB allow users to search databases using natural language instead of SQL-like query languages. While saving the users from having to learn query languages, multi-turn interaction with NLIDB usually involves multiple queries where contextual information is vital to understand the users' query intents. In this paper, we address a typical contextual understanding problem, termed as follow-up query analysis. In spite of its ubiquity, follow-up query analysis has not been well studied due to two primary obstacles: the multifarious nature of follow-up query scenarios and the lack of high-quality datasets. Our work summarizes typical follow-up query scenarios and provides a new FollowUp dataset with $1000$ query triples on 120 tables. Moreover, we propose a novel approach FANDA, which takes into account the structures of queries and employs a ranking model with weakly supervised max-margin learning. The experimental results on FollowUp demonstrate the superiority of FANDA over multiple baselines across multiple metrics.
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。