{"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/natural-language-to-structured-query","title":"Natural Language to Structured Query Generation via Meta-Learning","arxiv_id":"1803.02400","date":"2018-03-02","proceeding":"NAACL 2018 6","authors":["Po-Sen Huang","Chenglong Wang","Rishabh Singh","Wen-tau Yih","Xiaodong He"],"abstract":"In conventional supervised training, a model is trained to fit all the\ntraining examples. However, having a monolithic model may not always be the\nbest strategy, as examples could vary widely. In this work, we explore a\ndifferent learning protocol that treats each example as a unique pseudo-task,\nby reducing the original learning problem to a few-shot meta-learning scenario\nwith the help of a domain-dependent relevance function. When evaluated on the\nWikiSQL dataset, our approach leads to faster convergence and achieves\n1.1%-5.4% absolute accuracy gains over the non-meta-learning counterparts.","url_abs":"http://arxiv.org/abs/1803.02400v4","url_pdf":"http://arxiv.org/pdf/1803.02400v4.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":"natural-language-to-structured-query","repo_url":"https://github.com/Microsoft/PointerSQL","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"meta-learning","task_name":"Meta-Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/code-generation-on-wikisql","task":"Code Generation","dataset":"WikiSQL","model":"PT-MAML (Huang et al., 2018)","rank_in_archive_order":7,"of":10,"metrics":{"Exact Match Accuracy":"62.8","Execution Accuracy":"68.0"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1803.02400","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}