QUEST: A keyword search system for relational data based on semantic and machine learning techniques

Sonia Bergamaschi, Francesco Guerra, Matteo Interlandi, Raquel Trillo-Lado, Yannis Velegrakis

Research output: Contribution to journalArticle

25 Citations (Scopus)

Abstract

We showcase QUEST (QUEry generator for STructured sources), a search engine for relational databases that combines semantic and machine learning techniques for transforming keyword queries into meaningful SQL queries. The search engine relies on two approaches: the forward, providing mappings of keywords into database terms (names of tables and attributes, and domains of attributes), and the backward, computing the paths joining the data structures identified in the forward step. The results provided by the two approaches are combined within a probabilistic framework based on the Dempster-Shafer Theory. We demonstrate QUEST capabilities, and we show how, thanks to the flexibility obtained by the probabilistic combination of different techniques, QUEST is able to compute high quality results even with few training data and/or with hidden data sources such as those found in the Deep Web.

Original languageEnglish
Pages (from-to)1222-1225
Number of pages4
JournalProceedings of the VLDB Endowment
Volume6
Issue number12
Publication statusPublished - 1 Aug 2013

Fingerprint

Search engines
Learning systems
Semantics
Joining
Data structures

ASJC Scopus subject areas

  • Computer Science (miscellaneous)
  • Computer Science(all)

Cite this

Bergamaschi, S., Guerra, F., Interlandi, M., Trillo-Lado, R., & Velegrakis, Y. (2013). QUEST: A keyword search system for relational data based on semantic and machine learning techniques. Proceedings of the VLDB Endowment, 6(12), 1222-1225.

QUEST : A keyword search system for relational data based on semantic and machine learning techniques. / Bergamaschi, Sonia; Guerra, Francesco; Interlandi, Matteo; Trillo-Lado, Raquel; Velegrakis, Yannis.

In: Proceedings of the VLDB Endowment, Vol. 6, No. 12, 01.08.2013, p. 1222-1225.

Research output: Contribution to journalArticle

Bergamaschi, S, Guerra, F, Interlandi, M, Trillo-Lado, R & Velegrakis, Y 2013, 'QUEST: A keyword search system for relational data based on semantic and machine learning techniques', Proceedings of the VLDB Endowment, vol. 6, no. 12, pp. 1222-1225.
Bergamaschi S, Guerra F, Interlandi M, Trillo-Lado R, Velegrakis Y. QUEST: A keyword search system for relational data based on semantic and machine learning techniques. Proceedings of the VLDB Endowment. 2013 Aug 1;6(12):1222-1225.
Bergamaschi, Sonia ; Guerra, Francesco ; Interlandi, Matteo ; Trillo-Lado, Raquel ; Velegrakis, Yannis. / QUEST : A keyword search system for relational data based on semantic and machine learning techniques. In: Proceedings of the VLDB Endowment. 2013 ; Vol. 6, No. 12. pp. 1222-1225.
@article{cd409872a3624216914c1b21c9555b7a,
title = "QUEST: A keyword search system for relational data based on semantic and machine learning techniques",
abstract = "We showcase QUEST (QUEry generator for STructured sources), a search engine for relational databases that combines semantic and machine learning techniques for transforming keyword queries into meaningful SQL queries. The search engine relies on two approaches: the forward, providing mappings of keywords into database terms (names of tables and attributes, and domains of attributes), and the backward, computing the paths joining the data structures identified in the forward step. The results provided by the two approaches are combined within a probabilistic framework based on the Dempster-Shafer Theory. We demonstrate QUEST capabilities, and we show how, thanks to the flexibility obtained by the probabilistic combination of different techniques, QUEST is able to compute high quality results even with few training data and/or with hidden data sources such as those found in the Deep Web.",
author = "Sonia Bergamaschi and Francesco Guerra and Matteo Interlandi and Raquel Trillo-Lado and Yannis Velegrakis",
year = "2013",
month = "8",
day = "1",
language = "English",
volume = "6",
pages = "1222--1225",
journal = "Proceedings of the VLDB Endowment",
issn = "2150-8097",
publisher = "Very Large Data Base Endowment Inc.",
number = "12",

}

TY - JOUR

T1 - QUEST

T2 - A keyword search system for relational data based on semantic and machine learning techniques

AU - Bergamaschi, Sonia

AU - Guerra, Francesco

AU - Interlandi, Matteo

AU - Trillo-Lado, Raquel

AU - Velegrakis, Yannis

PY - 2013/8/1

Y1 - 2013/8/1

N2 - We showcase QUEST (QUEry generator for STructured sources), a search engine for relational databases that combines semantic and machine learning techniques for transforming keyword queries into meaningful SQL queries. The search engine relies on two approaches: the forward, providing mappings of keywords into database terms (names of tables and attributes, and domains of attributes), and the backward, computing the paths joining the data structures identified in the forward step. The results provided by the two approaches are combined within a probabilistic framework based on the Dempster-Shafer Theory. We demonstrate QUEST capabilities, and we show how, thanks to the flexibility obtained by the probabilistic combination of different techniques, QUEST is able to compute high quality results even with few training data and/or with hidden data sources such as those found in the Deep Web.

AB - We showcase QUEST (QUEry generator for STructured sources), a search engine for relational databases that combines semantic and machine learning techniques for transforming keyword queries into meaningful SQL queries. The search engine relies on two approaches: the forward, providing mappings of keywords into database terms (names of tables and attributes, and domains of attributes), and the backward, computing the paths joining the data structures identified in the forward step. The results provided by the two approaches are combined within a probabilistic framework based on the Dempster-Shafer Theory. We demonstrate QUEST capabilities, and we show how, thanks to the flexibility obtained by the probabilistic combination of different techniques, QUEST is able to compute high quality results even with few training data and/or with hidden data sources such as those found in the Deep Web.

UR - http://www.scopus.com/inward/record.url?scp=84891070608&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84891070608&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:84891070608

VL - 6

SP - 1222

EP - 1225

JO - Proceedings of the VLDB Endowment

JF - Proceedings of the VLDB Endowment

SN - 2150-8097

IS - 12

ER -