NALSpatial: A Natural Language Interface for Spatial Databases

Spatial databases play a vital role in a number of applications ranging from geographic information systems to location-based services. Application tasks typically access underlying spatial data to answer queries. However, non-experts lack the expertise necessary for formulating spatial queries. To...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE transactions on knowledge and data engineering Ročník 37; číslo 4; s. 2056 - 2070
Hlavní autoři: Liu, Mengyi, Wang, Xieyang, Xu, Jianqiu, Lu, Hua, Tong, Yongxin
Médium: Journal Article
Jazyk:angličtina
Vydáno: IEEE 01.04.2025
Témata:
ISSN:1041-4347, 1558-2191
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract Spatial databases play a vital role in a number of applications ranging from geographic information systems to location-based services. Application tasks typically access underlying spatial data to answer queries. However, non-experts lack the expertise necessary for formulating spatial queries. To fill in this gap, we propose an effective framework that translates na tural l anguage queries over spatial data into executable database queries, called NALSpatial. The framework consists of two core phases: (i) natural language understanding and (ii) natural language translation . Phase (i) extracts key entity information, comprehends the query intent and determines the query type by employing natural language processing techniques and deep learning algorithms. The key entities and query type are passed to phase (ii), which makes use of entity mapping rules and structured language models to construct executable database queries. NALSpatial supports dealing with five types of queries including (i) basic queries (e.g. distance and area) , (ii) range queries , (iii) nearest neighbor queries , (iv) spatial join queries and (v) aggregation queries . We develop NALSpatial in an open-source extensible database system SECONDO. Extensive experiments show that NALSpatial on average achieves response time of about 2.5 seconds, translatability of 95% and translation precision of 92%, outperforming three state-of-the-art methods.
AbstractList Spatial databases play a vital role in a number of applications ranging from geographic information systems to location-based services. Application tasks typically access underlying spatial data to answer queries. However, non-experts lack the expertise necessary for formulating spatial queries. To fill in this gap, we propose an effective framework that translates na tural l anguage queries over spatial data into executable database queries, called NALSpatial. The framework consists of two core phases: (i) natural language understanding and (ii) natural language translation . Phase (i) extracts key entity information, comprehends the query intent and determines the query type by employing natural language processing techniques and deep learning algorithms. The key entities and query type are passed to phase (ii), which makes use of entity mapping rules and structured language models to construct executable database queries. NALSpatial supports dealing with five types of queries including (i) basic queries (e.g. distance and area) , (ii) range queries , (iii) nearest neighbor queries , (iv) spatial join queries and (v) aggregation queries . We develop NALSpatial in an open-source extensible database system SECONDO. Extensive experiments show that NALSpatial on average achieves response time of about 2.5 seconds, translatability of 95% and translation precision of 92%, outperforming three state-of-the-art methods.
Author Liu, Mengyi
Xu, Jianqiu
Lu, Hua
Tong, Yongxin
Wang, Xieyang
Author_xml – sequence: 1
  givenname: Mengyi
  orcidid: 0009-0008-9149-3272
  surname: Liu
  fullname: Liu, Mengyi
  email: liumengyi@nuaa.edu.cn
  organization: College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China
– sequence: 2
  givenname: Xieyang
  orcidid: 0000-0003-3733-5405
  surname: Wang
  fullname: Wang, Xieyang
  email: xieyang@nuaa.edu.cn
  organization: College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China
– sequence: 3
  givenname: Jianqiu
  orcidid: 0000-0002-0929-5234
  surname: Xu
  fullname: Xu, Jianqiu
  email: jianqiu@nuaa.edu.cn
  organization: College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China
– sequence: 4
  givenname: Hua
  orcidid: 0000-0003-1199-6678
  surname: Lu
  fullname: Lu, Hua
  email: luhua@ruc.dk
  organization: Department of People and Technology, Roskilde University, Roskilde, Denmark
– sequence: 5
  givenname: Yongxin
  orcidid: 0000-0002-5598-0312
  surname: Tong
  fullname: Tong, Yongxin
  email: yxtong@buaa.edu.cn
  organization: State Key Laboratory of Software Development Environment, School of Computer Science and Engineering, Beihang University, Beijing, China
BookMark eNp9kLFOwzAURS1UJErhA5AY_AMpfrZTOwxIVVugIioDZY5ezXMVFJLKdgf-nlTtgBiY7hvuuXo6l2zQdi0xdgNiDCCKu_XLfDGWQuZjlcs8t-aMDaHPTEIBg_4WGjKttLlglzF-CiGssTBkD6tp-bbDVGNzz6d8hWkfsOEltts9bokv20TBoyPuu8BPTT7HhBuMFK_Yuccm0vUpR-z9cbGePWfl69NyNi0zp5RNGZDXEyOFBZxo40hJr73S9GE3BSgLSklFThpvc4mahHeQe4FegFOTQpIaMXPcdaGLMZCvXJ36X7o2BaybCkR10FAdNFQHDdVJQ0_CH3IX6i8M3_8yt0emJqJffSu1NUL9ABJUaSk
CODEN ITKEEH
CitedBy_id crossref_primary_10_1080_13658816_2025_2533322
Cites_doi 10.14778/2735461.2735468
10.1007/s00778-020-00645-2
10.14778/3641204.3641221
10.1145/3469830.3470892
10.1007/s11704-023-3133-6
10.1007/s00778-019-00567-8
10.14778/1687627.1687666
10.48550/ARXIV.1706.03762
10.1145/604045.604070
10.1145/3269206.3269247
10.14778/2994509.2994536
10.1145/3183713.3196909
10.1007/s41019-019-00109-w
10.14778/3603581.3603584
10.1561/1900000054
10.1007/s11431-020-1647-3
10.4324/9781003022022-6
10.1145/3318464.3389703
10.3115/v1/p14-5010
10.1145/2588555.2594519
10.1007/s11704-023-3008-x
10.1145/3035918.3054783
10.14778/3554821.3554876
10.1109/TKDE.2019.2948863
10.18653/v1/2023.findings-emnlp.750
10.14778/3574245.3574253
10.18653/v1/P19-1444
10.48550/arXiv.1810.04805
10.14778/2824032.2824042
10.1007/s00778-019-00568-7
10.1145/3589132.3625600
10.14778/3401960.3401970
10.1007/s44196-023-00188-8
10.1145/3593078.3593932
10.1007/s41019-020-00147-9
10.14778/3598581.3598596
10.1145/1247480.1247643
10.18653/v1/P17-1089
10.1007/s41019-023-00235-6
10.1145/3347146.3359069
10.1145/3143802
10.18653/v1/2020.acl-demos.14
10.14778/3579075.3579082
10.1145/3605943
10.14778/3457390.3457393
10.3115/1225403.1225421
10.14778/3554821.3554838
10.14778/3407790.3407858
10.1007/s00778-022-00759-9
10.14778/3554821.3554849
10.1007/s10707-023-00494-5
10.1109/ICDE51399.2021.00220
ContentType Journal Article
DBID 97E
RIA
RIE
AAYXX
CITATION
DOI 10.1109/TKDE.2025.3525587
DatabaseName IEEE Xplore (IEEE)
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE Xplore
CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Xplore
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
Computer Science
EISSN 1558-2191
EndPage 2070
ExternalDocumentID 10_1109_TKDE_2025_3525587
10824870
Genre orig-research
GrantInformation_xml – fundername: Opening Project of Key Laboratory of Ministry of Education
– fundername: National Natural Science Foundation of China; NSFC
  grantid: 62472217; U23A20296
  funderid: 10.13039/501100001809
– fundername: Southwest University of Science and Technology
  grantid: 24KFSK01
  funderid: 10.13039/501100004335
GroupedDBID -~X
.DC
0R~
1OL
29I
4.4
5GY
5VS
6IK
97E
9M8
AAJGR
AARMG
AASAJ
AAWTH
ABAZT
ABFSI
ABQJQ
ABVLG
ACGFO
ACIWK
AENEX
AETIX
AGQYO
AGSQL
AHBIQ
AI.
AIBXA
AKJIK
AKQYR
ALLEH
ALMA_UNASSIGNED_HOLDINGS
ASUFR
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CS3
DU5
E.L
EBS
EJD
F5P
HZ~
H~9
ICLAB
IEDLZ
IFIPE
IFJZH
IPLJI
JAVBF
LAI
M43
MS~
O9-
OCL
P2P
PQQKQ
RIA
RIE
RNI
RNS
RXW
RZB
TAE
TAF
TN5
UHB
VH1
AAYXX
CITATION
ID FETCH-LOGICAL-c338t-1ef4672081a647ce32f4f34ed8b913813323ec27f852a4e0fc15f0af01c3692e3
IEDL.DBID RIE
ISICitedReferencesCount 1
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001439548100032&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1041-4347
IngestDate Sat Nov 29 08:08:01 EST 2025
Tue Nov 18 22:33:19 EST 2025
Wed Aug 27 01:43:38 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 4
Language English
License https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
https://doi.org/10.15223/policy-029
https://doi.org/10.15223/policy-037
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c338t-1ef4672081a647ce32f4f34ed8b913813323ec27f852a4e0fc15f0af01c3692e3
ORCID 0000-0003-3733-5405
0000-0003-1199-6678
0009-0008-9149-3272
0000-0002-5598-0312
0000-0002-0929-5234
PageCount 15
ParticipantIDs crossref_citationtrail_10_1109_TKDE_2025_3525587
ieee_primary_10824870
crossref_primary_10_1109_TKDE_2025_3525587
PublicationCentury 2000
PublicationDate 2025-04-01
PublicationDateYYYYMMDD 2025-04-01
PublicationDate_xml – month: 04
  year: 2025
  text: 2025-04-01
  day: 01
PublicationDecade 2020
PublicationTitle IEEE transactions on knowledge and data engineering
PublicationTitleAbbrev TKDE
PublicationYear 2025
Publisher IEEE
Publisher_xml – name: IEEE
References ref13
ref12
ref56
ref15
ref14
ref53
ref52
ref11
ref55
ref10
ref54
ref17
ref16
Brown (ref37)
ref19
ref18
ref51
ref50
ref46
ref45
ref48
ref47
ref42
ref44
ref43
ref49
Ouyang (ref38)
ref8
ref7
ref9
ref4
ref3
ref6
ref5
ref40
Raffel (ref41) 2020; 21
ref35
ref34
ref36
ref31
ref30
ref33
ref32
ref2
ref1
ref39
ref23
ref26
ref25
ref20
ref22
ref21
Güting (ref24) 2010; 33
ref28
ref27
ref29
References_xml – ident: ref44
  doi: 10.14778/2735461.2735468
– ident: ref27
  doi: 10.1007/s00778-020-00645-2
– ident: ref55
  doi: 10.14778/3641204.3641221
– ident: ref5
  doi: 10.1145/3469830.3470892
– ident: ref14
  doi: 10.1007/s11704-023-3133-6
– start-page: 1877
  volume-title: Proc. Adv. Neural Inf. Process. Syst.
  ident: ref37
  article-title: Language models are few-shot learners
– volume: 33
  start-page: 56
  issue: 2
  year: 2010
  ident: ref24
  article-title: SECONDO: A platform for moving objects database research and for publishing and integrating research implementations
  publication-title: IEEE Data Eng. Bull.
– ident: ref52
  doi: 10.1007/s00778-019-00567-8
– ident: ref30
  doi: 10.14778/1687627.1687666
– ident: ref35
  doi: 10.48550/ARXIV.1706.03762
– ident: ref15
  doi: 10.1145/604045.604070
– ident: ref17
  doi: 10.1145/3269206.3269247
– ident: ref45
  doi: 10.14778/2994509.2994536
– ident: ref31
  doi: 10.1145/3183713.3196909
– volume: 21
  start-page: 140:1
  year: 2020
  ident: ref41
  article-title: Exploring the limits of transfer learning with a unified text-to-text transformer
  publication-title: J. Mach. Learn. Res.
– ident: ref51
  doi: 10.1007/s41019-019-00109-w
– ident: ref11
  doi: 10.14778/3603581.3603584
– ident: ref26
  doi: 10.1561/1900000054
– ident: ref39
  doi: 10.1007/s11431-020-1647-3
– ident: ref42
  doi: 10.4324/9781003022022-6
– ident: ref32
  doi: 10.1145/3318464.3389703
– ident: ref20
  doi: 10.3115/v1/p14-5010
– ident: ref43
  doi: 10.1145/2588555.2594519
– ident: ref53
  doi: 10.1007/s11704-023-3008-x
– ident: ref2
  doi: 10.1145/3035918.3054783
– ident: ref12
  doi: 10.14778/3554821.3554876
– ident: ref34
  doi: 10.1109/TKDE.2019.2948863
– ident: ref56
  doi: 10.18653/v1/2023.findings-emnlp.750
– ident: ref7
  doi: 10.14778/3574245.3574253
– ident: ref48
  doi: 10.18653/v1/P19-1444
– ident: ref40
  doi: 10.48550/arXiv.1810.04805
– ident: ref18
  doi: 10.14778/2824032.2824042
– ident: ref33
  doi: 10.1007/s00778-019-00568-7
– ident: ref25
  doi: 10.1145/3589132.3625600
– ident: ref23
  doi: 10.14778/3401960.3401970
– ident: ref3
  doi: 10.1007/s44196-023-00188-8
– ident: ref4
  doi: 10.1145/3593078.3593932
– ident: ref1
  doi: 10.1007/s41019-020-00147-9
– ident: ref8
  doi: 10.14778/3598581.3598596
– ident: ref16
  doi: 10.1145/1247480.1247643
– ident: ref50
  doi: 10.18653/v1/P17-1089
– ident: ref22
  doi: 10.1007/s41019-023-00235-6
– ident: ref47
  doi: 10.1145/3347146.3359069
– ident: ref9
  doi: 10.1145/3143802
– ident: ref21
  doi: 10.18653/v1/2020.acl-demos.14
– start-page: 27730
  volume-title: Proc. Adv. Neural Inf. Process. Syst.
  ident: ref38
  article-title: Training language models to follow instructions with human feedback
– ident: ref13
  doi: 10.14778/3579075.3579082
– ident: ref36
  doi: 10.1145/3605943
– ident: ref6
  doi: 10.14778/3457390.3457393
– ident: ref19
  doi: 10.3115/1225403.1225421
– ident: ref28
  doi: 10.14778/3554821.3554838
– ident: ref54
  doi: 10.14778/3407790.3407858
– ident: ref10
  doi: 10.1007/s00778-022-00759-9
– ident: ref29
  doi: 10.14778/3554821.3554849
– ident: ref46
  doi: 10.1007/s10707-023-00494-5
– ident: ref49
  doi: 10.1109/ICDE51399.2021.00220
SSID ssj0008781
Score 2.4705439
Snippet Spatial databases play a vital role in a number of applications ranging from geographic information systems to location-based services. Application tasks...
SourceID crossref
ieee
SourceType Enrichment Source
Index Database
Publisher
StartPage 2056
SubjectTerms Chatbots
Computational modeling
Data models
Distributed databases
Indexing
Natural language interface
Natural language processing
query processing
semantic parsing
Semantics
spatial database
Spatial databases
Structured Query Language
Translation
Title NALSpatial: A Natural Language Interface for Spatial Databases
URI https://ieeexplore.ieee.org/document/10824870
Volume 37
WOSCitedRecordID wos001439548100032&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
journalDatabaseRights – providerCode: PRVIEE
  databaseName: IEEE Xplore
  customDbUrl:
  eissn: 1558-2191
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0008781
  issn: 1041-4347
  databaseCode: RIE
  dateStart: 19890101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3NS8MwFA86POjB6Zw4v8jBk9CZJumSeBCG2xCU4WHCbiXNXkAYm2ydf79Jmo1eFLyU0r5A-aXJ-8h774fQHUl1wVKjkoxxm3Bt0kQJ6y6a-YIVKKS0gWxCjMdyOlXvsVg91MIAQEg-g66_DWf5s6XZ-FCZW-GSOgPbeej7QoiqWGu37UoRGEmde-GcIsZFPMJMiXqYvA6GzhWkWdc3_8x8-lxNCdVYVYJSGTX_-Tkn6Dhaj7hfTfcp2oNFCzW3zAw4LtQWOqq1GTxDTz5Dz2dO6_kj7uOxDr028FsMVeIQFbTaAHYWLI6SeKBL7XXcuo0-RsPJ80sSeRMS4xzOMknBuu2POmWve1wYYNRyyzjMZKFSp6EZowwMFVZmVHMg1qSZJdqS1LCeosDOUWOxXMAFwkabTFpBeu4ltwVot1ytdTaNAplpJTuIbIHMTWwq7rkt5nlwLojKPfa5xz6P2HfQ_W7IV9VR4y_htse9JlhBfvnL8yt06IdXqTXXqFGuNnCDDsx3-ble3YYf5gc4l7sZ
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3NS8MwFA-ignpwOifOzxw8CZ3NR9fEgzDcxmSzeJiwW0mzFxDGJvvw7zdJs7GLgpdS2tcSfu3Le7_kfSB0HxNVMKJllDBuIq40iWRq7EExl7AChRDGN5tIs0yMRvI9JKv7XBgA8MFn0HCnfi9_PNMrt1RmNVxQ62Bbhr6XcE5Jma61mXhF6nuSWoJhaRHjadjEJLF8HPbbHUsGadJw5T8TF0C3ZYa2-qp4s9Kt_HNAJ-g4-I-4VX7wU7QD0yqqrHsz4KCqVXS0VWjwDD27GD0XO60mT7iFM-WrbeBBWKzEfl3QKA3Y-rA4SOK2Wipn5RY19NHtDF96UeicEGlLOZcRAWMnQGrNvWryVAOjhhvGYSwKSayNZowy0DQ1IqGKQ2w0SUysTEw0a0oK7BztTmdTuEBYK50Ik8ZNe5ObApRVWGOsVyNBJEqKOorXQOY6lBV33S0muacXscwd9rnDPg_Y19HD5pGvsqbGX8I1h_uWYAn55S_X79BBb_g2yAevWf8KHbpXlYE212h3OV_BDdrX38vPxfzW_zw_JEq-YA
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=article&rft.atitle=NALSpatial%3A+A+Natural+Language+Interface+for+Spatial+Databases&rft.jtitle=IEEE+transactions+on+knowledge+and+data+engineering&rft.au=Liu%2C+Mengyi&rft.au=Wang%2C+Xieyang&rft.au=Xu%2C+Jianqiu&rft.au=Lu%2C+Hua&rft.date=2025-04-01&rft.pub=IEEE&rft.issn=1041-4347&rft.volume=37&rft.issue=4&rft.spage=2056&rft.epage=2070&rft_id=info:doi/10.1109%2FTKDE.2025.3525587&rft.externalDocID=10824870
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1041-4347&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1041-4347&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1041-4347&client=summon