FANDA: A Novel Approach to Perform Follow-up Query Analysis

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.