A probabilistic approach for mapping free-text queries to complex web forms

Research output: Book/ReportReportProfessional

20 Downloads (Pure)

Abstract

Web applications with complex interfaces consisting of multiple input fields should understand free-text queries. We propose a probabilistic approach to map parts of a free-text query to the fields of a complex web form. Our method uses token models rather than only static dictionaries to create this mapping, offering greater flexibility and requiring less domain knowledge than existing systems. We evaluate different implementations of our mapping model and show that our system effectively maps free-text queries without using a dictionary. If a dictionary is available, the performance increases and is significantly better than a rule-based baseline.
Original languageUndefined
Place of PublicationEnschede
PublisherCentre for Telematics and Information Technology (CTIT)
Number of pages12
Publication statusPublished - Jan 2012

Publication series

NameCTIT Technical Report Series
PublisherCentre for Telematics and Information Technology, University of Twente
No.TR-CTIT-12-33
ISSN (Print)1381-3625

Keywords

  • IR-84376
  • METIS-293267
  • EWI-22744

Cite this

Tjin-Kam-Jet, K., Trieschnigg, R. B., & Hiemstra, D. (2012). A probabilistic approach for mapping free-text queries to complex web forms. (CTIT Technical Report Series; No. TR-CTIT-12-33). Enschede: Centre for Telematics and Information Technology (CTIT).
Tjin-Kam-Jet, Kien ; Trieschnigg, Rudolf Berend ; Hiemstra, Djoerd. / A probabilistic approach for mapping free-text queries to complex web forms. Enschede : Centre for Telematics and Information Technology (CTIT), 2012. 12 p. (CTIT Technical Report Series; TR-CTIT-12-33).
@book{d8893a002cab4a1eb942914ba91a3181,
title = "A probabilistic approach for mapping free-text queries to complex web forms",
abstract = "Web applications with complex interfaces consisting of multiple input fields should understand free-text queries. We propose a probabilistic approach to map parts of a free-text query to the fields of a complex web form. Our method uses token models rather than only static dictionaries to create this mapping, offering greater flexibility and requiring less domain knowledge than existing systems. We evaluate different implementations of our mapping model and show that our system effectively maps free-text queries without using a dictionary. If a dictionary is available, the performance increases and is significantly better than a rule-based baseline.",
keywords = "IR-84376, METIS-293267, EWI-22744",
author = "Kien Tjin-Kam-Jet and Trieschnigg, {Rudolf Berend} and Djoerd Hiemstra",
year = "2012",
month = "1",
language = "Undefined",
series = "CTIT Technical Report Series",
publisher = "Centre for Telematics and Information Technology (CTIT)",
number = "TR-CTIT-12-33",
address = "Netherlands",

}

Tjin-Kam-Jet, K, Trieschnigg, RB & Hiemstra, D 2012, A probabilistic approach for mapping free-text queries to complex web forms. CTIT Technical Report Series, no. TR-CTIT-12-33, Centre for Telematics and Information Technology (CTIT), Enschede.

A probabilistic approach for mapping free-text queries to complex web forms. / Tjin-Kam-Jet, Kien; Trieschnigg, Rudolf Berend; Hiemstra, Djoerd.

Enschede : Centre for Telematics and Information Technology (CTIT), 2012. 12 p. (CTIT Technical Report Series; No. TR-CTIT-12-33).

Research output: Book/ReportReportProfessional

TY - BOOK

T1 - A probabilistic approach for mapping free-text queries to complex web forms

AU - Tjin-Kam-Jet, Kien

AU - Trieschnigg, Rudolf Berend

AU - Hiemstra, Djoerd

PY - 2012/1

Y1 - 2012/1

N2 - Web applications with complex interfaces consisting of multiple input fields should understand free-text queries. We propose a probabilistic approach to map parts of a free-text query to the fields of a complex web form. Our method uses token models rather than only static dictionaries to create this mapping, offering greater flexibility and requiring less domain knowledge than existing systems. We evaluate different implementations of our mapping model and show that our system effectively maps free-text queries without using a dictionary. If a dictionary is available, the performance increases and is significantly better than a rule-based baseline.

AB - Web applications with complex interfaces consisting of multiple input fields should understand free-text queries. We propose a probabilistic approach to map parts of a free-text query to the fields of a complex web form. Our method uses token models rather than only static dictionaries to create this mapping, offering greater flexibility and requiring less domain knowledge than existing systems. We evaluate different implementations of our mapping model and show that our system effectively maps free-text queries without using a dictionary. If a dictionary is available, the performance increases and is significantly better than a rule-based baseline.

KW - IR-84376

KW - METIS-293267

KW - EWI-22744

M3 - Report

T3 - CTIT Technical Report Series

BT - A probabilistic approach for mapping free-text queries to complex web forms

PB - Centre for Telematics and Information Technology (CTIT)

CY - Enschede

ER -

Tjin-Kam-Jet K, Trieschnigg RB, Hiemstra D. A probabilistic approach for mapping free-text queries to complex web forms. Enschede: Centre for Telematics and Information Technology (CTIT), 2012. 12 p. (CTIT Technical Report Series; TR-CTIT-12-33).