Issues in learning an ontology from text

Christopher Brewster; Simon Jupp; Joanne Luciano; David Shotton; Robert Stevens; Ziqi Zhang

Issues in learning an ontology from text

Christopher Brewster, Simon Jupp, Joanne Luciano, David Shotton, Robert Stevens, Ziqi Zhang

Research output: Chapter in Book/Published conference output › Conference publication

Abstract

Ontology construction for any domain is a labour intensive and complex process. Any methodology that can reduce the cost and increase efficiency has the potential to make a major impact in the life sciences. This paper describes an experiment in ontology construction from text for the Animal Behaviour domain. Our objective was to see how much could be done in a simple and rapid manner using a corpus of journal papers. We used a sequence of text processing steps, and describe the different choices made to clean the input, to derive a set of terms and to structure those terms in a hierarchy. We were able in a very short space of time to construct a 17000 term ontology with a high percentage of suitable terms. We describe some of the challenges, especially
that of focusing the ontology appropriately given a starting point of a heterogeneous corpus.

Original language	English
Title of host publication	The 11th Annual Bio-Ontologies Meeting
Editors	Phillip Lord, Nigam Shah, Susanna-Assunta Sansone, Matthew Cockerill
Number of pages	4
Publication status	Published - 2008
Event	11th Annual Bio-Ontologies Meeting - Toronto, Canada Duration: 20 Jul 2008 → …

Conference

Conference	11th Annual Bio-Ontologies Meeting
Country/Territory	Canada
City	Toronto
Period	20/07/08 → …

Cite this

@inproceedings{c87dfbdd2fe445b894d1f7f58e9c245a,

title = "Issues in learning an ontology from text",

abstract = "Ontology construction for any domain is a labour intensive and complex process. Any methodology that can reduce the cost and increase efficiency has the potential to make a major impact in the life sciences. This paper describes an experiment in ontology construction from text for the Animal Behaviour domain. Our objective was to see how much could be done in a simple and rapid manner using a corpus of journal papers. We used a sequence of text processing steps, and describe the different choices made to clean the input, to derive a set of terms and to structure those terms in a hierarchy. We were able in a very short space of time to construct a 17000 term ontology with a high percentage of suitable terms. We describe some of the challenges, especiallythat of focusing the ontology appropriately given a starting point of a heterogeneous corpus.",

author = "Christopher Brewster and Simon Jupp and Joanne Luciano and David Shotton and Robert Stevens and Ziqi Zhang",

year = "2008",

language = "English",

editor = "Phillip Lord and Nigam Shah and Susanna-Assunta Sansone and Matthew Cockerill",

booktitle = "The 11th Annual Bio-Ontologies Meeting",

note = "11th Annual Bio-Ontologies Meeting ; Conference date: 20-07-2008",

}

TY - GEN

T1 - Issues in learning an ontology from text

AU - Brewster, Christopher

AU - Jupp, Simon

AU - Luciano, Joanne

AU - Shotton, David

AU - Stevens, Robert

AU - Zhang, Ziqi

PY - 2008

Y1 - 2008

N2 - Ontology construction for any domain is a labour intensive and complex process. Any methodology that can reduce the cost and increase efficiency has the potential to make a major impact in the life sciences. This paper describes an experiment in ontology construction from text for the Animal Behaviour domain. Our objective was to see how much could be done in a simple and rapid manner using a corpus of journal papers. We used a sequence of text processing steps, and describe the different choices made to clean the input, to derive a set of terms and to structure those terms in a hierarchy. We were able in a very short space of time to construct a 17000 term ontology with a high percentage of suitable terms. We describe some of the challenges, especiallythat of focusing the ontology appropriately given a starting point of a heterogeneous corpus.

AB - Ontology construction for any domain is a labour intensive and complex process. Any methodology that can reduce the cost and increase efficiency has the potential to make a major impact in the life sciences. This paper describes an experiment in ontology construction from text for the Animal Behaviour domain. Our objective was to see how much could be done in a simple and rapid manner using a corpus of journal papers. We used a sequence of text processing steps, and describe the different choices made to clean the input, to derive a set of terms and to structure those terms in a hierarchy. We were able in a very short space of time to construct a 17000 term ontology with a high percentage of suitable terms. We describe some of the challenges, especiallythat of focusing the ontology appropriately given a starting point of a heterogeneous corpus.

M3 - Conference publication

BT - The 11th Annual Bio-Ontologies Meeting

A2 - Lord, Phillip

A2 - Shah, Nigam

A2 - Sansone, Susanna-Assunta

A2 - Cockerill, Matthew

T2 - 11th Annual Bio-Ontologies Meeting

Y2 - 20 July 2008

ER -

Issues in learning an ontology from text

Abstract

Conference

Fingerprint

Cite this