xDBTagger: explainable natural language interface to databases using keyword mappings and schema graph

Simple item page
buir.contributor.authorUlusoy, Özgür
dc.citation.epage321en_US
dc.citation.issueNumber2
dc.citation.spage301
dc.citation.volumeNumber33
dc.contributor.authorUsta, A.
dc.contributor.authorKarakayalı, A.
dc.contributor.authorUlusoy, Özgür
dc.date.accessioned2024-03-12T08:16:44Z
dc.date.available2024-03-12T08:16:44Z
dc.date.issued2023-08-23
dc.departmentDepartment of Computer Engineering
dc.description.abstractRecently, numerous studies have been proposed to attack the natural language interfaces to data-bases (NLIDB) problem by researchers either as a conventional pipeline-based or an end-to-end deep-learning-based solution. Although each approach has its own advantages and drawbacks, regardless of the approach preferred, both approaches exhibit black-box nature, which makes it difficult for potential users to comprehend the rationale behind the decisions made by the intelligent system to produce the translated SQL. Given that NLIDB targets users with little to no technical background, having interpretable and explainable solutions becomes crucial, which has been overlooked in the recent studies. To this end, we propose xDBTagger, an explainable hybrid translation pipeline that explains the decisions made along the way to the user both textually and visually. We also evaluate xDBTagger quantitatively in three real-world relational databases. The evaluation results indicate that in addition to being lightweight, fast, and fully explainable, xDBTagger is also competitive in terms of translation accuracy compared to both pipeline-based and end-to-end deep learning approaches.
dc.description.provenanceMade available in DSpace on 2024-03-12T08:16:44Z (GMT). No. of bitstreams: 1 xDBTagger_explainable_natural_language_interface_to_databases_using_keyword_mappings_and_schema_graph.pdf: 1983263 bytes, checksum: a132aac705d0d76fe57141e18dae4605 (MD5) Previous issue date: 2023-08-23en
dc.identifier.doi10.1007/s00778-023-00809-w
dc.identifier.eissn0949-877X
dc.identifier.issn1066-8888
dc.identifier.urihttps://hdl.handle.net/11693/114554
dc.language.isoEnglish
dc.publisherSpringer
dc.relation.isversionofhttps://dx.doi.org/10.1007/s00778-023-00809-w
dc.source.titleVLDB Journal
dc.subjectNatural language interface for databases
dc.subjectNLIDB
dc.subjectText-to-SQL
dc.subjectMulti-task learning
dc.subjectExplainable artificial intelligence
dc.subjectXAI
dc.titlexDBTagger: explainable natural language interface to databases using keyword mappings and schema graph
dc.typeArticle

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
xDBTagger_explainable_natural_language_interface_to_databases_using_keyword_mappings_and_schema_graph.pdf
Size:
1.88 MB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
2.01 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Department of Computer Engineering