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

arXiv: https://arxiv.org/abs/1901.08259 · HTML: https://mlsanity.com/paper/1901.08259/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Jan 2019.

## Built on by (most cited first, 2 of 2)

- [Neural Approaches to Conversational Information Retrieval](https://mlsanity.com/paper/2201.05176/) (2022)
- [MODS: Moderating a Mixture of Document Speakers to Summarize Debatable Queries in Document Collections](https://mlsanity.com/paper/2502.00322/) (2025)

## Abstract (arXiv)

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.