{"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/semantic-parsing-with-syntax-and-table-aware","title":"Semantic Parsing with Syntax- and Table-Aware SQL Generation","arxiv_id":"1804.08338","date":"2018-04-23","proceeding":"ACL 2018 7","authors":["Yibo Sun","Duyu Tang","Nan Duan","Jianshu ji","Guihong Cao","Xiaocheng Feng","Bing Qin","Ting Liu","Ming Zhou"],"abstract":"We present a generative model to map natural language questions into SQL\nqueries. Existing neural network based approaches typically generate a SQL\nquery word-by-word, however, a large portion of the generated results are\nincorrect or not executable due to the mismatch between question words and\ntable contents. Our approach addresses this problem by considering the\nstructure of table and the syntax of SQL language. The quality of the generated\nSQL query is significantly improved through (1) learning to replicate content\nfrom column names, cells or SQL keywords; and (2) improving the generation of\nWHERE clause by leveraging the column-cell relation. Experiments are conducted\non WikiSQL, a recently released dataset with the largest question-SQL pairs.\nOur approach significantly improves the state-of-the-art execution accuracy\nfrom 69.0% to 74.4%.","url_abs":"http://arxiv.org/abs/1804.08338v1","url_pdf":"http://arxiv.org/pdf/1804.08338v1.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":[],"tasks":[{"task_slug":"semantic-parsing","task_name":"Semantic Parsing"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/code-generation-on-wikisql","task":"Code Generation","dataset":"WikiSQL","model":"STAMP+RL (Sun et al., 2018)+","rank_in_archive_order":4,"of":10,"metrics":{"Exact Match Accuracy":"61.0","Execution Accuracy":"74.6"},"uses_additional_data":false},{"leaderboard":"/sota/code-generation-on-wikisql","task":"Code Generation","dataset":"WikiSQL","model":"STAMP (Sun et al., 2018)+","rank_in_archive_order":5,"of":10,"metrics":{"Exact Match Accuracy":"60.7","Execution Accuracy":"74.4"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1804.08338","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}