{"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/typesql-knowledge-based-type-aware-neural","title":"TypeSQL: Knowledge-based Type-Aware Neural Text-to-SQL Generation","arxiv_id":"1804.09769","date":"2018-04-25","proceeding":"NAACL 2018 6","authors":["Tao Yu","Zifan Li","Zilin Zhang","Rui Zhang","Dragomir Radev"],"abstract":"Interacting with relational databases through natural language helps users of\nany background easily query and analyze a vast amount of data. This requires a\nsystem that understands users' questions and converts them to SQL queries\nautomatically. In this paper we present a novel approach, TypeSQL, which views\nthis problem as a slot filling task. Additionally, TypeSQL utilizes type\ninformation to better understand rare entities and numbers in natural language\nquestions. We test this idea on the WikiSQL dataset and outperform the prior\nstate-of-the-art by 5.5% in much less time. We also show that accessing the\ncontent of databases can significantly improve the performance when users'\nqueries are not well-formed. TypeSQL gets 82.6% accuracy, a 17.5% absolute\nimprovement compared to the previous content-sensitive model.","url_abs":"http://arxiv.org/abs/1804.09769v1","url_pdf":"http://arxiv.org/pdf/1804.09769v1.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":"typesql-knowledge-based-type-aware-neural","repo_url":"https://github.com/taoyds/typesql","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"slot-filling","task_name":"Slot Filling"},{"task_slug":"text-to-sql","task_name":"Text to SQL"},{"task_slug":"text-to-sql","task_name":"Text-To-SQL"},{"task_slug":"type","task_name":"Vocal Bursts Type Prediction"},{"task_slug":"slot-filling-1","task_name":"slot-filling"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/code-generation-on-wikisql","task":"Code Generation","dataset":"WikiSQL","model":"TypeSQL+TC (Yu et al., 2018)+","rank_in_archive_order":2,"of":10,"metrics":{"Execution Accuracy":"82.6"},"uses_additional_data":false},{"leaderboard":"/sota/code-generation-on-wikisql","task":"Code Generation","dataset":"WikiSQL","model":"TypeSQL (Yu et al., 2018)","rank_in_archive_order":6,"of":10,"metrics":{"Execution Accuracy":"73.5"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1804.09769","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}