FANDA: A Novel Approach to Perform Follow-up Query Analysis
This work addresses a contextual understanding problem for users of NLIDBs, but it is incremental as it builds on existing research with a new dataset and method.
The paper tackles the problem of follow-up query analysis in Natural Language Interfaces to Databases by introducing a new dataset with 1000 query triples and proposing the FANDA method, which achieves superior performance over baselines on multiple metrics.
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.