{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T09:51:49Z","timestamp":1773481909242,"version":"3.50.1"},"reference-count":23,"publisher":"China Science Publishing & Media Ltd.","issue":"2","license":[{"start":{"date-parts":[[2023,2,9]],"date-time":"2023-02-09T00:00:00Z","timestamp":1675900800000},"content-version":"vor","delay-in-days":131,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["direct.mit.edu"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,5,9]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n               <jats:p>Text-to-SQL aims at translating textual questions into the corresponding SQL queries. Aggregate tables are widely created for high-frequent queries. Although text-to-SQL has emerged as an important task, recent studies paid little attention to the task over aggregate tables. The increased aggregate tables bring two challenges: (1) mapping of natural language questions and relational databases will suffer from more ambiguity, (2) modern models usually adopt self-attention mechanism to encode database schema and question. The mechanism is of quadratic time complexity, which will make inferring more time-consuming as input sequence length grows. In this paper, we introduce a novel approach named WAGG for text-to-SQL over aggregate tables. To effectively select among ambiguous items, we propose a relation selection mechanism for relation computing. To deal with high computation costs, we introduce a dynamical pruning strategy to discard unrelated items that are common for aggregate tables. We also construct a new large-scale dataset SpiderwAGG extended from Spider dataset for validation, where extensive experiments show the effectiveness and efficiency of our proposed method with 4% increase of accuracy and 15% decrease of inference time w.r.t a strong baseline RAT-SQL.<\/jats:p>","DOI":"10.1162\/dint_a_00194","type":"journal-article","created":{"date-parts":[[2023,2,9]],"date-time":"2023-02-09T16:16:41Z","timestamp":1675959401000},"page":"457-474","update-policy":"https:\/\/doi.org\/10.1162\/mitpressjournals.corrections.policy","source":"Crossref","is-referenced-by-count":5,"title":["Towards Text-to-SQL over Aggregate Tables"],"prefix":"10.3724","volume":"5","author":[{"given":"Shuqin","family":"Li","sequence":"first","affiliation":[{"name":"College of Design and Innovation, Tongji University, Shanghai, 200092"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kaibin","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Software, Tongji University, Shanghai, 201804"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zeyang","family":"Zhuang","sequence":"additional","affiliation":[{"name":"School of Software, Tongji University, Shanghai, 201804"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haofen","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Design and Innovation, Tongji University, Shanghai, 200092"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Ma","sequence":"additional","affiliation":[{"name":"School of Automotive Studies, Tongji University, Shanghai, 201804"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"2026","published-online":{"date-parts":[[2022,10,1]]},"reference":[{"key":"2023050918333159800_ref1","volume-title":"Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning","author":"Zhong","year":"2017"},{"key":"2023050918333159800_ref2","first-page":"3911","volume-title":"Spider: A large-scale human-labeled dataset for complex and cross-domain semantic parsing and text-to-SQL task","author":"Yu","year":"2018"},{"key":"2023050918333159800_ref3","first-page":"6923","volume-title":"DuSQL: A Large-Scale and Pragmatic Chinese Text-to-SQL Dataset","author":"Wang","year":"2020"},{"key":"2023050918333159800_ref4","volume-title":"TableQA: a Large-Scale Chinese Text-to-SQL Dataset for Table-Aware SQL Generation","author":"Sun","year":"2020"},{"key":"2023050918333159800_ref5","first-page":"7567","volume-title":"RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parsers","author":"Wang","year":"2020"},{"key":"2023050918333159800_ref6","first-page":"2218","volume-title":"Service-oriented Text-to-SQL Parsing","author":"Hu","year":"2020"},{"key":"2023050918333159800_ref7","first-page":"2747","volume-title":"ATHENA++: natural language querying for complex nested SQL queries","author":"Sen","year":"2020"},{"key":"2023050918333159800_ref8","volume-title":"Robust Text-to-SQL Generation with Execution-Guided Decoding","author":"Wang","year":"2018"},{"key":"2023050918333159800_ref9","first-page":"356","article-title":"Margy Ross","volume-title":"The Data Warehouse Toolkit: The Complete Guide to Dimensional Modeling","author":"Kimball","year":"2002","edition":"Second ed."},{"key":"2023050918333159800_ref10","first-page":"4870","volume-title":"Bridging Textual and Tabular Data for Cross-Domain Text-to-SQL Semantic Parsing","author":"Lin","year":"2020"},{"issue":"12","key":"2023050918333159800_ref11","first-page":"11106","article-title":"Informer: Beyond efficient transformer for long sequence time-series forecasting","volume":"35","author":"Zhou","year":"2020","journal-title":"In: Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"2023050918333159800_ref12","first-page":"4171","volume-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","author":"Devlin","year":"2018"},{"key":"2023050918333159800_ref13","first-page":"8413","volume-title":"TABERT: Pretraining for Joint Understanding of Textual and Tabular Data","author":"Yin","year":"2020"},{"key":"2023050918333159800_ref14","first-page":"4560","volume-title":"Representing schema structure with graph neural networks for text-to-SQL parsing","author":"Bogin","year":"2021"},{"key":"2023050918333159800_ref15","first-page":"5999","volume-title":"Attention is all you need","author":"Vaswani","year":"2017"},{"key":"2023050918333159800_ref16","first-page":"3477","volume-title":"Beyond I.I.D.: Three levels of generalization for question answering on knowledge bases","author":"Gu","year":"2020"},{"key":"2023050918333159800_ref17","first-page":"183","article-title":"BREAK it down: A question understanding benchmark","volume":"8","author":"Wolfson","year":"2020","journal-title":"In: Transactions of the Association for Computational Linguistics"},{"key":"2023050918333159800_ref18","first-page":"2319","volume-title":"Duoquest: A Dual-Specification System for Expressive SQL Queries","author":"Baik","year":"2020"},{"key":"2023050918333159800_ref19","first-page":"1026","volume-title":"HybridQA: A dataset of multi-hop question answering over tabular and textual data","author":"Chen","year":"2020"},{"key":"2023050918333159800_ref20","first-page":"2319","volume-title":"Open Question Answering over Tables and Text","author":"Wenhu","year":"2021"},{"key":"2023050918333159800_ref21","first-page":"440","volume-title":"A syntactic neural model for general-purpose code generation","author":"Yin","year":"2017"},{"key":"2023050918333159800_ref22","first-page":"1332","volume-title":"Building a semantic parser overnight","author":"Wang","year":"2015"},{"key":"2023050918333159800_ref23","first-page":"396","volume-title":"Semantic evaluation for Text-to-SQL with distilled test suites","author":"Zhong","year":"2020"}],"container-title":["Data Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/direct.mit.edu\/dint\/article-pdf\/5\/2\/457\/2089791\/dint_a_00194.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/direct.mit.edu\/dint\/article-pdf\/5\/2\/457\/2089791\/dint_a_00194.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,14]],"date-time":"2025-03-14T07:41:06Z","timestamp":1741938066000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.sciengine.com\/doi\/10.1162\/dint_a_00194"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,1]]},"references-count":23,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2023,5,9]]}},"URL":"https:\/\/doi.org\/10.1162\/dint_a_00194","relation":{},"ISSN":["2641-435X"],"issn-type":[{"value":"2641-435X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2023]]},"published":{"date-parts":[[2022,10,1]]}}}