{"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/an-end-to-end-neural-natural-language","title":"An End-to-end Neural Natural Language Interface for Databases","arxiv_id":"1804.00401","date":"2018-04-02","proceeding":null,"authors":["Prasetya Utama","Nathaniel Weir","Fuat Basik","Carsten Binnig","Ugur Cetintemel","Benjamin Hättasch","Amir Ilkhechi","Shekar Ramaswamy","Arif Usta"],"abstract":"The ability to extract insights from new data sets is critical for decision\nmaking. Visual interactive tools play an important role in data exploration\nsince they provide non-technical users with an effective way to visually\ncompose queries and comprehend the results. Natural language has recently\ngained traction as an alternative query interface to databases with the\npotential to enable non-expert users to formulate complex questions and\ninformation needs efficiently and effectively. However, understanding natural\nlanguage questions and translating them accurately to SQL is a challenging\ntask, and thus Natural Language Interfaces for Databases (NLIDBs) have not yet\nmade their way into practical tools and commercial products.\n  In this paper, we present DBPal, a novel data exploration tool with a natural\nlanguage interface. DBPal leverages recent advances in deep models to make\nquery understanding more robust in the following ways: First, DBPal uses a deep\nmodel to translate natural language statements to SQL, making the translation\nprocess more robust to paraphrasing and other linguistic variations. Second, to\nsupport the users in phrasing questions without knowing the database schema and\nthe query features, DBPal provides a learned auto-completion model that\nsuggests partial query extensions to users during query formulation and thus\nhelps to write complex queries.","url_abs":"http://arxiv.org/abs/1804.00401v1","url_pdf":"http://arxiv.org/pdf/1804.00401v1.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":"an-end-to-end-neural-natural-language","repo_url":"https://github.com/DataManagementLab/ParaphraseBench","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"an-end-to-end-neural-natural-language","repo_url":"https://github.com/nkapetanas/dbpal","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"decision-making","task_name":"Decision Making"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1804.00401","atlas_url":"https://app.syntology.ai/?focus=1804.00401","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}