@article{Liu_Chen_Lou_Jin_Zhang_2019, title={FANDA: A Novel Approach to Perform Follow-Up Query Analysis}, volume={33}, url={https://ojs.aaai.org/index.php/AAAI/article/view/4651}, DOI={10.1609/aaai.v33i01.33016770}, abstractNote={<p>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 FA<span style="font-variant: small-caps;">N</span>D<span style="font-variant: small-caps;">A</span>, 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 FA<span style="font-variant: small-caps;">N</span>D<span style="font-variant: small-caps;">A</span> over multiple baselines across multiple metrics.</p>}, number={01}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Liu, Qian and Chen, Bei and Lou, Jian-Guang and Jin, Ge and Zhang, Dongmei}, year={2019}, month={Jul.}, pages={6770-6777} }