{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/fanda-a-novel-approach-to-perform-follow-up","title":"FANDA: A Novel Approach to Perform Follow-up Query Analysis","arxiv_id":"1901.08259","date":"2019-01-24","proceeding":null,"authors":["Qian Liu","Bei Chen","Jian-Guang Lou","Ge Jin","Dongmei Zhang"],"abstract":"Recent work on Natural Language Interfaces to Databases (NLIDB) has attracted\nconsiderable attention. NLIDB allow users to search databases using natural\nlanguage instead of SQL-like query languages. While saving the users from\nhaving to learn query languages, multi-turn interaction with NLIDB usually\ninvolves multiple queries where contextual information is vital to understand\nthe users' query intents. In this paper, we address a typical contextual\nunderstanding problem, termed as follow-up query analysis. In spite of its\nubiquity, follow-up query analysis has not been well studied due to two primary\nobstacles: the multifarious nature of follow-up query scenarios and the lack of\nhigh-quality datasets. Our work summarizes typical follow-up query scenarios\nand provides a new FollowUp dataset with $1000$ query triples on 120 tables.\nMoreover, we propose a novel approach FANDA, which takes into account the\nstructures of queries and employs a ranking model with weakly supervised\nmax-margin learning. The experimental results on FollowUp demonstrate the\nsuperiority of FANDA over multiple baselines across multiple metrics.","url_abs":"http://arxiv.org/abs/1901.08259v1","url_pdf":"http://arxiv.org/pdf/1901.08259v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"fanda-a-novel-approach-to-perform-follow-up","repo_url":"https://github.com/SivilTaram/FollowUp","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[{"slug":"followup","name":"FollowUp","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1901.08259","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}