Coral: Corpus access in controlled language

Tobias Kuhn, Stefan Höfler

Research output: Contribution to JournalArticleAcademicpeer-review

Abstract

In this paper, we present Coral, an interface in which complex corpus queries can be expressed in a controlled subset of natural English. With the help of a predictive editor, users can compose queries and submit them to the Coral system, which then automatically translates them into formal AQL statements.We give an overview of the controlled natural language developed for Coral and describe the functionalities of the predictive editor provided for it. We also report on a user experiment in which the system was evaluated. The results show that, with Coral, corpora of annotated texts can be queried more easily and more quickly than with the existing ANNIS interface. Our system demonstrates that complex corpora can be accessed without the need to learn a complicated, formal query language.

Original languageEnglish
Pages (from-to)187-206
Number of pages20
JournalCorpora
Volume7
Issue number2
DOIs
Publication statusPublished - Nov 2012
Externally publishedYes

Fingerprint

language
editor
functionality
experiment
Controlled
Language
Functionality
Experiment
Query Language
Natural Language

Cite this

Kuhn, Tobias ; Höfler, Stefan. / Coral : Corpus access in controlled language. In: Corpora. 2012 ; Vol. 7, No. 2. pp. 187-206.
@article{9ac891d820914d339937829b733d59d6,
title = "Coral: Corpus access in controlled language",
abstract = "In this paper, we present Coral, an interface in which complex corpus queries can be expressed in a controlled subset of natural English. With the help of a predictive editor, users can compose queries and submit them to the Coral system, which then automatically translates them into formal AQL statements.We give an overview of the controlled natural language developed for Coral and describe the functionalities of the predictive editor provided for it. We also report on a user experiment in which the system was evaluated. The results show that, with Coral, corpora of annotated texts can be queried more easily and more quickly than with the existing ANNIS interface. Our system demonstrates that complex corpora can be accessed without the need to learn a complicated, formal query language.",
author = "Tobias Kuhn and Stefan H{\"o}fler",
year = "2012",
month = "11",
doi = "10.3366/cor.2012.0026",
language = "English",
volume = "7",
pages = "187--206",
journal = "Corpora",
issn = "1749-5032",
publisher = "Edinburgh University Press",
number = "2",

}

Coral : Corpus access in controlled language. / Kuhn, Tobias; Höfler, Stefan.

In: Corpora, Vol. 7, No. 2, 11.2012, p. 187-206.

Research output: Contribution to JournalArticleAcademicpeer-review

TY - JOUR

T1 - Coral

T2 - Corpus access in controlled language

AU - Kuhn, Tobias

AU - Höfler, Stefan

PY - 2012/11

Y1 - 2012/11

N2 - In this paper, we present Coral, an interface in which complex corpus queries can be expressed in a controlled subset of natural English. With the help of a predictive editor, users can compose queries and submit them to the Coral system, which then automatically translates them into formal AQL statements.We give an overview of the controlled natural language developed for Coral and describe the functionalities of the predictive editor provided for it. We also report on a user experiment in which the system was evaluated. The results show that, with Coral, corpora of annotated texts can be queried more easily and more quickly than with the existing ANNIS interface. Our system demonstrates that complex corpora can be accessed without the need to learn a complicated, formal query language.

AB - In this paper, we present Coral, an interface in which complex corpus queries can be expressed in a controlled subset of natural English. With the help of a predictive editor, users can compose queries and submit them to the Coral system, which then automatically translates them into formal AQL statements.We give an overview of the controlled natural language developed for Coral and describe the functionalities of the predictive editor provided for it. We also report on a user experiment in which the system was evaluated. The results show that, with Coral, corpora of annotated texts can be queried more easily and more quickly than with the existing ANNIS interface. Our system demonstrates that complex corpora can be accessed without the need to learn a complicated, formal query language.

UR - http://www.scopus.com/inward/record.url?scp=84881222451&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84881222451&partnerID=8YFLogxK

U2 - 10.3366/cor.2012.0026

DO - 10.3366/cor.2012.0026

M3 - Article

VL - 7

SP - 187

EP - 206

JO - Corpora

JF - Corpora

SN - 1749-5032

IS - 2

ER -