Applying Text Mining Methods to Construct a Domain Ontology from Definitions

Margarida Ramos; Rute Costa

doi:http://doi.org/10.6092/issn.2532-8816/19284

Applying Text Mining Methods to Construct a Domain Ontology from Definitions

Margarida Ramos, Rute Costa

Research output: Contribution to journal › Article › peer-review

3 Downloads (Pure)

Abstract

This paper aims to describe a text-mining approach on a domain corpus (cork) within the theoretical framework of the dual dimension of terminology to create a terminological dictionary and correlate it with an ontology. We will make some considerations on (i) domain specificities; (ii) lexical markers; (iii) automatic corpus processing using Sketch Engine; (iv) representation of lexical networks using CmapTools; and (v) representation of the concept system using Protégé.
The goal of the ontology is to logically support the coherence and quality of the natural language definitions contained in the terminological resource.

Original language	English
Pages (from-to)	103-143
Number of pages	41
Journal	Umanistica Digitale
Issue number	18
DOIs	https://doi.org/10.6092/issn.2532-8816/19284
Publication status	Published - 2024

Keywords

Terminology
Definition
Domain-ontology
Knowledge-rich information
Domain corpus
Terminological dictionary

Access to Document

http://doi.org/10.6092/issn.2532-8816/19284Licence: CC BY

Applying Text Mining Methods Final published version, 1.08 MBLicence: CC BY

https://umanisticadigitale.unibo.it/article/view/19284Licence: CC BY

1 Participation in conference

Multilingual digital terminology today. Design, representation formats and management systems (MDTT 2023)
Maria Rute Vilhena Costa (Chair), Giorgio Di Nunzio (Chair), Federica Vezzani (Chair), Raquel Alves da Silva (Member of programme committee), Ana Salgado (Member of programme committee), Sara Carvalho (Organiser) & Margarida Ramos (Organiser)
29 Jun 2023 → 30 Jun 2023
Activity: Participating in or organising an event › Participation in conference

File

Cite this

@article{4d2066846a8b4cd3900218a31a9444c7,

title = "Applying Text Mining Methods to Construct a Domain Ontology from Definitions",

abstract = "This paper aims to describe a text-mining approach on a domain corpus (cork) within the theoretical framework of the dual dimension of terminology to create a terminological dictionary and correlate it with an ontology. We will make some considerations on (i) domain specificities; (ii) lexical markers; (iii) automatic corpus processing using Sketch Engine; (iv) representation of lexical networks using CmapTools; and (v) representation of the concept system using Prot{\'e}g{\'e}. The goal of the ontology is to logically support the coherence and quality of the natural language definitions contained in the terminological resource.",

keywords = "Terminology, Definition, Domain-ontology, Knowledge-rich information, Domain corpus, Terminological dictionary",

author = "Margarida Ramos and Rute Costa",

note = "info:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/UIDB%2F03213%2F2020/PT# info:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/UIDP%2F03213%2F2020/PT# UIDB/03213/2020 UIDP/03213/2020",

year = "2024",

doi = "http://doi.org/10.6092/issn.2532-8816/19284",

language = "English",

pages = "103--143",

journal = "Umanistica Digitale",

issn = "2532-8816",

publisher = "University of Bologna",

number = "18",

}

TY - JOUR

T1 - Applying Text Mining Methods to Construct a Domain Ontology from Definitions

AU - Ramos, Margarida

AU - Costa, Rute

N1 - info:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/UIDB%2F03213%2F2020/PT# info:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/UIDP%2F03213%2F2020/PT# UIDB/03213/2020 UIDP/03213/2020

PY - 2024

Y1 - 2024

N2 - This paper aims to describe a text-mining approach on a domain corpus (cork) within the theoretical framework of the dual dimension of terminology to create a terminological dictionary and correlate it with an ontology. We will make some considerations on (i) domain specificities; (ii) lexical markers; (iii) automatic corpus processing using Sketch Engine; (iv) representation of lexical networks using CmapTools; and (v) representation of the concept system using Protégé. The goal of the ontology is to logically support the coherence and quality of the natural language definitions contained in the terminological resource.

AB - This paper aims to describe a text-mining approach on a domain corpus (cork) within the theoretical framework of the dual dimension of terminology to create a terminological dictionary and correlate it with an ontology. We will make some considerations on (i) domain specificities; (ii) lexical markers; (iii) automatic corpus processing using Sketch Engine; (iv) representation of lexical networks using CmapTools; and (v) representation of the concept system using Protégé. The goal of the ontology is to logically support the coherence and quality of the natural language definitions contained in the terminological resource.

KW - Terminology

KW - Definition

KW - Domain-ontology

KW - Knowledge-rich information

KW - Domain corpus

KW - Terminological dictionary

U2 - http://doi.org/10.6092/issn.2532-8816/19284

DO - http://doi.org/10.6092/issn.2532-8816/19284

M3 - Article

SN - 2532-8816

SP - 103

EP - 143

JO - Umanistica Digitale

JF - Umanistica Digitale

IS - 18

ER -

Applying Text Mining Methods to Construct a Domain Ontology from Definitions

Abstract

Keywords

Access to Document

Fingerprint

Activities

Multilingual digital terminology today. Design, representation formats and management systems (MDTT 2023)

Cite this