SQL Synthesis with Input-Output Example Based on Deep Learning
In recent years, an increasing number of people rely on data manipulation tasks to complete their work. However, many of these users lack programming background and find it challenging to write complex programs, especially SQL. As a result, the automatic synthesis of SQL has become a hot research to...
Gespeichert in:
| Veröffentlicht in: | Proceedings of ... International Joint Conference on Neural Networks S. 1 - 8 |
|---|---|
| Hauptverfasser: | , , , , |
| Format: | Tagungsbericht |
| Sprache: | Englisch |
| Veröffentlicht: |
IEEE
18.06.2023
|
| Schlagworte: | |
| ISSN: | 2161-4407 |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| Abstract | In recent years, an increasing number of people rely on data manipulation tasks to complete their work. However, many of these users lack programming background and find it challenging to write complex programs, especially SQL. As a result, the automatic synthesis of SQL has become a hot research topic. This process, called Query Reverse Engineering (QRE), involves automatically synthesizing SQL based on input-output tables provided by users. While most SQL synthesizers focus on structures that do not use deep learning, we propose a new SQL synthesis method that lever-ages the superiority of deep learning. Our method uses a deep neural network (DNN) to predict the correlation between the input-output table and DSL operators, eliminate irrelevant operators, and improve the efficiency of SQL synthesis. We have implemented the SQL synthesis system, Solid, based on this method. The system introduces the Deep Neural Network (DNN) based on SQUARES, one of the best query synthesizers. To verify the effectiveness of our proposed method, we conducted experiments using a simple neural network structure. The results show that our method outperforms SQUARES, with an increased success rate of stereo synthesis from 80% to 89.1%, and a reduced average synthesis time from 251s to 130s. |
|---|---|
| AbstractList | In recent years, an increasing number of people rely on data manipulation tasks to complete their work. However, many of these users lack programming background and find it challenging to write complex programs, especially SQL. As a result, the automatic synthesis of SQL has become a hot research topic. This process, called Query Reverse Engineering (QRE), involves automatically synthesizing SQL based on input-output tables provided by users. While most SQL synthesizers focus on structures that do not use deep learning, we propose a new SQL synthesis method that lever-ages the superiority of deep learning. Our method uses a deep neural network (DNN) to predict the correlation between the input-output table and DSL operators, eliminate irrelevant operators, and improve the efficiency of SQL synthesis. We have implemented the SQL synthesis system, Solid, based on this method. The system introduces the Deep Neural Network (DNN) based on SQUARES, one of the best query synthesizers. To verify the effectiveness of our proposed method, we conducted experiments using a simple neural network structure. The results show that our method outperforms SQUARES, with an increased success rate of stereo synthesis from 80% to 89.1%, and a reduced average synthesis time from 251s to 130s. |
| Author | Zhang, Shun Wang, Huixian Dou, Quansheng Tang, Huanling Pan, Hao |
| Author_xml | – sequence: 1 givenname: Shun surname: Zhang fullname: Zhang, Shun email: 1258107605@qq.com organization: College of Computer Science and Technology, Shandong Technology and Business University,Yantai,China – sequence: 2 givenname: Quansheng surname: Dou fullname: Dou, Quansheng email: douqsh@sdtbu.edu.cn organization: College of Computer Science and Technology, Shandong Technology and Business University,Yantai,China – sequence: 3 givenname: Huanling surname: Tang fullname: Tang, Huanling email: thL01@163.com organization: College of Computer Science and Technology, Shandong Technology and Business University,Yantai,China – sequence: 4 givenname: Hao surname: Pan fullname: Pan, Hao email: 17853826608@126.com organization: College of Computer Science and Technology, Shandong Technology and Business University,Yantai,China – sequence: 5 givenname: Huixian surname: Wang fullname: Wang, Huixian email: 931218953@qq.com organization: College of Computer Science and Technology, Shandong Technology and Business University,Yantai,China |
| BookMark | eNo1j9FKwzAYhaMouE7fwIu8QGf-Jk2TG0Hr1ErZkOn1SJu_LrJlpenQvb0BFQ58cDgczknImd97JIQCmwEwfVO9lItFLnLBZhnL-AwYaACpTkgCUuZCKVmwUzLJQEIqBCsuSBLCJ4tZrfmE3K5ea7o6-nGDwQX65cYNrXx_GNPlYYyg82-z67dI701AS_eePiD2tEYzeOc_Lsl5Z7YBr_44Je-P87fyOa2XT1V5V6cuY2JMARAa3QllJFhr4r7GcC5QtwVvuJWmLTRgVPTjlw65atCCzZS1rTWKT8n1b69DxHU_uJ0Zjuv_s_wH80xLzA |
| ContentType | Conference Proceeding |
| DBID | 6IE 6IH CBEJK RIE RIO |
| DOI | 10.1109/IJCNN54540.2023.10191168 |
| DatabaseName | IEEE Electronic Library (IEL) Conference Proceedings IEEE Proceedings Order Plan (POP) 1998-present by volume IEEE Xplore All Conference Proceedings IEEE Electronic Library (IEL) IEEE Proceedings Order Plans (POP) 1998-present |
| DatabaseTitleList | |
| Database_xml | – sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science |
| EISBN | 1665488670 9781665488679 |
| EISSN | 2161-4407 |
| EndPage | 8 |
| ExternalDocumentID | 10191168 |
| Genre | orig-research |
| GrantInformation_xml | – fundername: National Natural Science Foundation of China grantid: 61976125,61976124,61772319,61773244 funderid: 10.13039/501100001809 |
| GroupedDBID | 6IE 6IF 6IH 6IK 6IL 6IM 6IN AAJGR AAWTH ABLEC ADZIZ ALMA_UNASSIGNED_HOLDINGS BEFXN BFFAM BGNUA BKEBE BPEOZ CBEJK CHZPO IEGSK IJVOP IPLJI M43 OCL RIE RIL RIO RNS |
| ID | FETCH-LOGICAL-i204t-11e1b9f48a61dda168ba334e9c73b3d6ac791e91e8ba454fe38bed1d28ddcda83 |
| IEDL.DBID | RIE |
| ISICitedReferencesCount | 0 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001046198701010&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| IngestDate | Wed Aug 27 02:10:43 EDT 2025 |
| IsPeerReviewed | false |
| IsScholarly | false |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-i204t-11e1b9f48a61dda168ba334e9c73b3d6ac791e91e8ba454fe38bed1d28ddcda83 |
| PageCount | 8 |
| ParticipantIDs | ieee_primary_10191168 |
| PublicationCentury | 2000 |
| PublicationDate | 2023-June-18 |
| PublicationDateYYYYMMDD | 2023-06-18 |
| PublicationDate_xml | – month: 06 year: 2023 text: 2023-June-18 day: 18 |
| PublicationDecade | 2020 |
| PublicationTitle | Proceedings of ... International Joint Conference on Neural Networks |
| PublicationTitleAbbrev | IJCNN |
| PublicationYear | 2023 |
| Publisher | IEEE |
| Publisher_xml | – name: IEEE |
| SSID | ssj0023993 |
| Score | 1.8354485 |
| Snippet | In recent years, an increasing number of people rely on data manipulation tasks to complete their work. However, many of these users lack programming... |
| SourceID | ieee |
| SourceType | Publisher |
| StartPage | 1 |
| SubjectTerms | Artificial neural networks Deep learning Program Synthesis Query Reverse Engineering Reverse engineering Search problems Solids SQL Synthesizers Training |
| Title | SQL Synthesis with Input-Output Example Based on Deep Learning |
| URI | https://ieeexplore.ieee.org/document/10191168 |
| WOSCitedRecordID | wos001046198701010&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LTwMhECa28eCpPmp8h4NXainbhb14sLaxpllrqklvDTCD6WXbtFuj_17Y7mo8eDAhgRAIZIbJDDDzDSHXYPw58oY8U7EAFjmFTHOIfKvtOs51uYSC0yOZpmo6TcZlsHoRC4OIhfMZtkKz-MuHhd2EpzIv4f52wWNVIzUp422w1vftKmjaylWnndwMH3tp2g34cq2QIbxVzf2VRaVQIoPGP5ffJ82fcDw6_lY0B2QHs0PSqPIx0FI8j8jt5HlEJ5-Zt-nW8zUNT6x0mPlB7GmT-4r2P3QAA6Z3XnUBXWT0HnFJS4jVtyZ5HfRfeg-szI_A5p12lDPOkZvERUrHHED7nRktRISJlcIIiLWVCUdffL8nhEOhDAKHjgKwoJU4JvVskeEJoRa6OraRNNaYyDrQoIXxtoRRNgCmilPSDPSYLbcQGLOKFGd_9J-TvUD14FPF1QWp56sNXpJd-57P16urgnFf2YqaUw |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LT8MwDI5gIMFpPIZ4kwPXjqZJ2_TCgbFpg1KGNqTdpiROp126aesQ_HuSrh3iwAEpUqwokSI7ke3E_ozQLUhzjowh7_CAgsNSrh1BgBnKTb009UkIhaTjMEn4aBT1y2T1IhdGa10En-mmJYu_fJiplX0qMzfceBck4Ntox2fMc9fpWhv_yuraKljHje56T60k8S3CXNPWCG9Wq3_VUSnUSKf-zw0coMZPQh7ub1TNIdrS2RGqVxUZcHlBj9H94C3Gg6_MWHXL6RLbR1bcy8wk53WVmw63P4WFA8YPRnkBnmX4Ues5LkFWJw303mkPW12nrJDgTD2X5Q4hmsgoZVwEBECYnUlBKdORCqmkEAgVRkSbZsYNI1JNudRAwOMACgSnJ6iWzTJ9irACXwSKhVJJyVQKAgSVxpqQXFnIVHqGGpYf4_kaBGNcseL8j_EbtNcdvsTjuJc8X6B9KwEbYUX4Jarli5W-QrvqI58uF9eFEL8BEGqdmg |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=proceeding&rft.title=Proceedings+of+...+International+Joint+Conference+on+Neural+Networks&rft.atitle=SQL+Synthesis+with+Input-Output+Example+Based+on+Deep+Learning&rft.au=Zhang%2C+Shun&rft.au=Dou%2C+Quansheng&rft.au=Tang%2C+Huanling&rft.au=Pan%2C+Hao&rft.date=2023-06-18&rft.pub=IEEE&rft.eissn=2161-4407&rft.spage=1&rft.epage=8&rft_id=info:doi/10.1109%2FIJCNN54540.2023.10191168&rft.externalDocID=10191168 |