{"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/learning-contextual-representations-for","title":"Learning Contextual Representations for Semantic Parsing with Generation-Augmented Pre-Training","arxiv_id":"2012.10309","date":"2020-12-18","proceeding":null,"authors":["Peng Shi","Patrick Ng","Zhiguo Wang","Henghui Zhu","Alexander Hanbo Li","Jun Wang","Cicero Nogueira dos santos","Bing Xiang"],"abstract":"Most recently, there has been significant interest in learning contextual representations for various NLP tasks, by leveraging large scale text corpora to train large neural language models with self-supervised learning objectives, such as Masked Language Model (MLM). However, based on a pilot study, we observe three issues of existing general-purpose language models when they are applied to text-to-SQL semantic parsers: fail to detect column mentions in the utterances, fail to infer column mentions from cell values, and fail to compose complex SQL queries. To mitigate these issues, we present a model pre-training framework, Generation-Augmented Pre-training (GAP), that jointly learns representations of natural language utterances and table schemas by leveraging generation models to generate pre-train data. GAP MODEL is trained on 2M utterance-schema pairs and 30K utterance-schema-SQL triples, whose utterances are produced by generative models. Based on experimental results, neural semantic parsers that leverage GAP MODEL as a representation encoder obtain new state-of-the-art results on both SPIDER and CRITERIA-TO-SQL benchmarks.","url_abs":"https://arxiv.org/abs/2012.10309v1","url_pdf":"https://arxiv.org/pdf/2012.10309v1.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":"learning-contextual-representations-for","repo_url":"https://github.com/awslabs/gap-text2sql","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"learning-contextual-representations-for","repo_url":"https://github.com/c4ai/gap-text2sql","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"learning-contextual-representations-for","repo_url":"https://github.com/dmirlab-group/sadga","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"},{"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/semantic-parsing-on-spider","task":"Semantic Parsing","dataset":"spider","model":"RATSQL + GAP","rank_in_archive_order":7,"of":10,"metrics":{"Accuracy":"69.7"},"uses_additional_data":false},{"leaderboard":"/sota/text-to-sql-on-spider","task":"Text-To-SQL","dataset":"spider","model":"RATSQL + GAP","rank_in_archive_order":19,"of":20,"metrics":{"Exact Match Accuracy (Dev)":"71.8"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2012.10309","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}