RHB-Net: A Relation-aware Historical Bridging Network for Text2SQL Auto-Completion
Uloženo v:
| Název: | RHB-Net: A Relation-aware Historical Bridging Network for Text2SQL Auto-Completion |
|---|---|
| Autoři: | Zheng, Bolong, Bi, Lei, Xi, Ruijie, Chen, Lu, Gao, Yunjun, Zhou, Xiaofang, Jensen, Christian S. |
| Informace o vydavateli: | Association for Computing Machinery, Inc |
| Rok vydání: | 2023 |
| Sbírka: | The Hong Kong University of Science and Technology: HKUST Institutional Repository |
| Témata: | Text2SQL, auto-completion, database, query language |
| Popis: | Test2SQL, a natural language interface to database querying, has seen considerable improvement, in part due to advances in deep learning. However, despite recent improvement, existing Text2SQL proposals allow only input in the form of complete questions. This leaves behind users who struggle to formulate complete questions, e.g., because they lack database expertise or are unfamiliar with the underlying database schema. To address this shortcoming, we study the novel problem of Text2SQL Auto-Completion (TSAC) that extends Text2SQL to also take partial or incomplete questions as input. Specifically, the TSAC problem is to predict the complete, executable SQL query. To solve the problem, we propose a novel Relation-aware Historical Bridging Network (RHB-Net) that consists of a relation-aware union encoder and an extraction-generation sensitive decoder. RHB-Net models relations between questions and database schemas and predicts the ambiguous intents expressed in partial queries. We also propose two optimization strategies: historical query bridging that fuses historical database queries, and a dynamic context construction that prevents repeated generation of the same SQL elements. Extensive experiments with real-world data offer evidence that RHB-Net is capable of outperforming baseline algorithms. |
| Druh dokumentu: | conference object |
| Jazyk: | English |
| Relation: | https://doi.org/10.1145/3539618.3591759; http://gateway.isiknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=LinksAMR&SrcApp=PARTNER_APP&DestLinkType=FullRecord&DestApp=WOS&KeyUT=001118084001051 |
| DOI: | 10.1145/3539618.3591759 |
| Dostupnost: | http://repository.hkust.edu.hk/ir/Record/1783.1-130838 https://doi.org/10.1145/3539618.3591759 http://lbdiscover.ust.hk/uresolver?url_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rfr_id=info:sid/HKUST:SPI&rft.genre=article&rft.issn=&rft.volume=&rft.issue=&rft.date=2023&rft.spage=1458&rft.aulast=Zheng&rft.aufirst=Bolong&rft.atitle=RHB-Net%3A+A+Relation-aware+Historical+Bridging+Network+for+Text2SQL+Auto-Completion&rft.title=SIGIR+2023+-+Proceedings+of+the+46th+International+ACM+SIGIR+Conference+on+Research+and+Development+in+Information+Retrieval http://gateway.isiknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=LinksAMR&SrcApp=PARTNER_APP&DestLinkType=FullRecord&DestApp=WOS&KeyUT=001118084001051 http://www.scopus.com/record/display.url?eid=2-s2.0-85168672571&origin=inward |
| Přístupové číslo: | edsbas.E355D1CA |
| Databáze: | BASE |
Nájsť tento článok vo Web of Science | Abstrakt: | Test2SQL, a natural language interface to database querying, has seen considerable improvement, in part due to advances in deep learning. However, despite recent improvement, existing Text2SQL proposals allow only input in the form of complete questions. This leaves behind users who struggle to formulate complete questions, e.g., because they lack database expertise or are unfamiliar with the underlying database schema. To address this shortcoming, we study the novel problem of Text2SQL Auto-Completion (TSAC) that extends Text2SQL to also take partial or incomplete questions as input. Specifically, the TSAC problem is to predict the complete, executable SQL query. To solve the problem, we propose a novel Relation-aware Historical Bridging Network (RHB-Net) that consists of a relation-aware union encoder and an extraction-generation sensitive decoder. RHB-Net models relations between questions and database schemas and predicts the ambiguous intents expressed in partial queries. We also propose two optimization strategies: historical query bridging that fuses historical database queries, and a dynamic context construction that prevents repeated generation of the same SQL elements. Extensive experiments with real-world data offer evidence that RHB-Net is capable of outperforming baseline algorithms. |
|---|---|
| DOI: | 10.1145/3539618.3591759 |