{"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/improving-generalization-in-language-model","title":"Improving Generalization in Language Model-Based Text-to-SQL Semantic Parsing: Two Simple Semantic Boundary-Based Techniques","arxiv_id":"2305.17378","date":"2023-05-27","proceeding":null,"authors":["Daking Rai","Bailin Wang","Yilun Zhou","Ziyu Yao"],"abstract":"Compositional and domain generalization present significant challenges in semantic parsing, even for state-of-the-art semantic parsers based on pre-trained language models (LMs). In this study, we empirically investigate improving an LM's generalization in semantic parsing with two simple techniques: at the token level, we introduce a token preprocessing method to preserve the semantic boundaries of tokens produced by LM tokenizers; at the sequence level, we propose to use special tokens to mark the boundaries of components aligned between input and output. Our experimental results on two text-to-SQL semantic parsing datasets show that our token preprocessing, although simple, can substantially improve the LM performance on both types of generalization, and our component boundary marking method is particularly helpful for compositional generalization.","url_abs":"https://arxiv.org/abs/2305.17378v1","url_pdf":"https://arxiv.org/pdf/2305.17378v1.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":"improving-generalization-in-language-model","repo_url":"https://github.com/dakingrai/ood-generalization-semantic-boundary-techniques","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"domain-generalization","task_name":"Domain Generalization"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"semantic-parsing","task_name":"Semantic 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":[{"leaderboard":"/sota/text-to-sql-on-spider","task":"Text-To-SQL","dataset":"spider","model":"T5-3B+NatSQL+Token Preprocessing","rank_in_archive_order":9,"of":20,"metrics":{"Exact Match Accuracy (Dev)":"69.4","Execution Accuracy (Dev)":"73.7","Execution Accuracy (Test)":"78"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2305.17378","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}