Translating synthetic natural language to database queries with a polyglot deep learning framework

Abstract The number of databases as well as their size and complexity is increasing. This creates a barrier to use especially for non-experts, who have to come to grips with the nature of the data, the way it has been represented in the database, and the specific query languages or user interfaces b...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Adrián Bazaga, Nupur Gunwant, Gos Micklem
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/1cd9a00efc4c4af795a5321ffe3aca56
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:1cd9a00efc4c4af795a5321ffe3aca56
record_format	dspace
spelling	oai:doaj.org-article:1cd9a00efc4c4af795a5321ffe3aca562021-12-02T18:50:52ZTranslating synthetic natural language to database queries with a polyglot deep learning framework10.1038/s41598-021-98019-32045-2322https://doaj.org/article/1cd9a00efc4c4af795a5321ffe3aca562021-09-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-98019-3https://doaj.org/toc/2045-2322Abstract The number of databases as well as their size and complexity is increasing. This creates a barrier to use especially for non-experts, who have to come to grips with the nature of the data, the way it has been represented in the database, and the specific query languages or user interfaces by which data are accessed. These difficulties worsen in research settings, where it is common to work with many different databases. One approach to improving this situation is to allow users to pose their queries in natural language. In this work we describe a machine learning framework, Polyglotter, that in a general way supports the mapping of natural language searches to database queries. Importantly, it does not require the creation of manually annotated data for training and therefore can be applied easily to multiple domains. The framework is polyglot in the sense that it supports multiple different database engines that are accessed with a variety of query languages, including SQL and Cypher. Furthermore Polyglotter supports multi-class queries. Good performance is achieved on both toy and real databases, as well as a human-annotated WikiSQL query set. Thus Polyglotter may help database maintainers make their resources more accessible.Adrián BazagaNupur GunwantGos MicklemNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-11 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Adrián Bazaga Nupur Gunwant Gos Micklem Translating synthetic natural language to database queries with a polyglot deep learning framework
description	Abstract The number of databases as well as their size and complexity is increasing. This creates a barrier to use especially for non-experts, who have to come to grips with the nature of the data, the way it has been represented in the database, and the specific query languages or user interfaces by which data are accessed. These difficulties worsen in research settings, where it is common to work with many different databases. One approach to improving this situation is to allow users to pose their queries in natural language. In this work we describe a machine learning framework, Polyglotter, that in a general way supports the mapping of natural language searches to database queries. Importantly, it does not require the creation of manually annotated data for training and therefore can be applied easily to multiple domains. The framework is polyglot in the sense that it supports multiple different database engines that are accessed with a variety of query languages, including SQL and Cypher. Furthermore Polyglotter supports multi-class queries. Good performance is achieved on both toy and real databases, as well as a human-annotated WikiSQL query set. Thus Polyglotter may help database maintainers make their resources more accessible.
format	article
author	Adrián Bazaga Nupur Gunwant Gos Micklem
author_facet	Adrián Bazaga Nupur Gunwant Gos Micklem
author_sort	Adrián Bazaga
title	Translating synthetic natural language to database queries with a polyglot deep learning framework
title_short	Translating synthetic natural language to database queries with a polyglot deep learning framework
title_full	Translating synthetic natural language to database queries with a polyglot deep learning framework
title_fullStr	Translating synthetic natural language to database queries with a polyglot deep learning framework
title_full_unstemmed	Translating synthetic natural language to database queries with a polyglot deep learning framework
title_sort	translating synthetic natural language to database queries with a polyglot deep learning framework
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/1cd9a00efc4c4af795a5321ffe3aca56
work_keys_str_mv	AT adrianbazaga translatingsyntheticnaturallanguagetodatabasequerieswithapolyglotdeeplearningframework AT nupurgunwant translatingsyntheticnaturallanguagetodatabasequerieswithapolyglotdeeplearningframework AT gosmicklem translatingsyntheticnaturallanguagetodatabasequerieswithapolyglotdeeplearningframework
_version_	1718377489088118784

Translating synthetic natural language to database queries with a polyglot deep learning framework

Ejemplares similares