{"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/proton-probing-schema-linking-information","title":"Proton: Probing Schema Linking Information from Pre-trained Language Models for Text-to-SQL Parsing","arxiv_id":"2206.14017","date":"2022-06-28","proceeding":null,"authors":["Lihan Wang","Bowen Qin","Binyuan Hui","Bowen Li","Min Yang","Bailin Wang","Binhua Li","Fei Huang","Luo Si","Yongbin Li"],"abstract":"The importance of building text-to-SQL parsers which can be applied to new databases has long been acknowledged, and a critical step to achieve this goal is schema linking, i.e., properly recognizing mentions of unseen columns or tables when generating SQLs. In this work, we propose a novel framework to elicit relational structures from large-scale pre-trained language models (PLMs) via a probing procedure based on Poincar\\'e distance metric, and use the induced relations to augment current graph-based parsers for better schema linking. Compared with commonly-used rule-based methods for schema linking, we found that probing relations can robustly capture semantic correspondences, even when surface forms of mentions and entities differ. Moreover, our probing procedure is entirely unsupervised and requires no additional parameters. Extensive experiments show that our framework sets new state-of-the-art performance on three benchmarks. We empirically verify that our probing procedure can indeed find desired relational structures through qualitative analysis. Our code can be found at https://github.com/AlibabaResearch/DAMO-ConvAI.","url_abs":"https://arxiv.org/abs/2206.14017v2","url_pdf":"https://arxiv.org/pdf/2206.14017v2.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":"proton-probing-schema-linking-information","repo_url":"https://github.com/alibabaresearch/damo-convai","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"proton-probing-schema-linking-information","repo_url":"https://github.com/AlibabaResearch/DAMO-ConvAI/tree/main/proton","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"sql-parsing","task_name":"SQL Parsing"},{"task_slug":"text-to-sql","task_name":"Text to SQL"},{"task_slug":"text-to-sql","task_name":"Text-To-SQL"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2206.14017","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}