Dealing with specialized co-text in text mining: the verbal terminological collocations

Margarida Ramos; Rute  Costa; Christophe Bernard Jean-Joseph Roche

Dealing with specialized co-text in text mining: the verbal terminological collocations

Margarida Ramos, Rute Costa, Christophe Bernard Jean-Joseph Roche

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

161 Downloads (Pure)

Abstract

The aim of this paper is to organise lexical and conceptual knowledge by analysing a domain-specific corpus. The domain we focus on is the cork industry. Through the analysis of the corpus, we have found that some common verbs in Portuguese, such as “choose” and “separate” acquire a specialised value in the field under study. This was the starting point for the analysis of the terminological collocations where verbs are the core constituents. For the analysis of these verbal terminological collocations, we used natural language processing techniques, building simple and complex CQL structures with RegEx. The outcome of this analysis permits us to introduce a distinction between polylexical terms and terminological collocations. The terminological collocation is a reality of great relevance in specialised discourse, but unlike terms, it is not defined by conceptual criteria, but by morphological and syntactic criteria.

Original language	English
Title of host publication	Actes de la conférence TOTh 2019
Subtitle of host publication	Terminologie & Ontologie: Théories et Applications
Editors	Christophe Roche, Catherine Brun
Place of Publication	Chambéry
Publisher	Presses Universitaires Savoie Mont Blanc
Pages	339-362
Number of pages	23
ISBN (Print)	978-2-919732-80-7
Publication status	Published - 6 Jul 2020
Event	T.T.M. 2019 : Terminologie et Fouille de Textes: Session Satellite en parallèle avec la Conférence TOTh 2019 - Chambéry, France Duration: 6 Jun 2019 → 7 Jun 2019 http://toth.condillac.org/ttm-2019

Publication series

Name	Terminologica
Publisher	Presses Universitaires Savoie Mont Blanc
ISSN (Electronic)	2607-5008

Conference

Conference	T.T.M. 2019 : Terminologie et Fouille de Textes
Abbreviated title	TTM 2019
Country/Territory	France
City	Chambéry
Period	6/06/19 → 7/06/19
Internet address	http://toth.condillac.org/ttm-2019

Keywords

Text mining
Terminology
Lexicography
Collocation
Compounding
Definition
Natural language processing
Verbal terminological collocation

Access to Document

Article TOTh 2019Final published version, 519 KBLicence: Unspecified

http://ontologia.fr/TOTh/Conference/TOTh2019/TOTh_2019.pdfLicence: Unspecified

Doctoral Scholarship
Viegas Ramos, M. (Recipient), Oct 2015
Prize: Fellowship awarded competitively

Dealing with specialized co-text in text mining: The verbal terminological collocations
Viegas Ramos, M. (Speaker) & Costa, M. R. V. (Speaker)
6 Jun 2019
Activity: Talk or presentation › Oral presentation
T.T.M. 2019 : Terminologie et Fouille de Textes
Viegas Ramos, M. (Speaker) & Costa, M. R. V. (Speaker)
6 Jun 2019 → 7 Jun 2019
Activity: Participating in or organising an event › Participation in conference

File

Cite this

Ramos, M., Costa, R., & Roche, C. B. J.-J. (2020). Dealing with specialized co-text in text mining: the verbal terminological collocations. In C. Roche, & C. Brun (Eds.), Actes de la conférence TOTh 2019: Terminologie & Ontologie: Théories et Applications (pp. 339-362). Article 19 (Terminologica). Presses Universitaires Savoie Mont Blanc. http://ontologia.fr/TOTh/Conference/TOTh2019/TOTh_2019.pdf

Ramos, Margarida ; Costa, Rute ; Roche, Christophe Bernard Jean-Joseph. / Dealing with specialized co-text in text mining : the verbal terminological collocations. Actes de la conférence TOTh 2019: Terminologie & Ontologie: Théories et Applications. editor / Christophe Roche ; Catherine Brun. Chambéry : Presses Universitaires Savoie Mont Blanc, 2020. pp. 339-362 (Terminologica).

@inproceedings{72a6896a342c4b0a97e5d1d73d348aa1,

title = "Dealing with specialized co-text in text mining: the verbal terminological collocations",

abstract = "The aim of this paper is to organise lexical and conceptual knowledge by analysing a domain-specific corpus. The domain we focus on is the cork industry. Through the analysis of the corpus, we have found that some common verbs in Portuguese, such as “choose” and “separate” acquire a specialised value in the field under study. This was the starting point for the analysis of the terminological collocations where verbs are the core constituents. For the analysis of these verbal terminological collocations, we used natural language processing techniques, building simple and complex CQL structures with RegEx. The outcome of this analysis permits us to introduce a distinction between polylexical terms and terminological collocations. The terminological collocation is a reality of great relevance in specialised discourse, but unlike terms, it is not defined by conceptual criteria, but by morphological and syntactic criteria.",

keywords = "Text mining, Terminology, Lexicography, Collocation, Compounding, Definition, Natural language processing, Verbal terminological collocation",

author = "Margarida Ramos and Rute Costa and Roche, \{Christophe Bernard Jean-Joseph\}",

note = "UIDB/03213/2020 UIDP/03213/2020 UID/LIN/03213/2019 ; T.T.M. 2019 : Terminologie et Fouille de Textes : Session Satellite en parall{\`e}le avec la Conf{\'e}rence TOTh 2019, TTM 2019 ; Conference date: 06-06-2019 Through 07-06-2019",

year = "2020",

month = jul,

day = "6",

language = "English",

isbn = "978-2-919732-80-7",

series = "Terminologica",

publisher = "Presses Universitaires Savoie Mont Blanc",

pages = "339--362",

editor = "Christophe Roche and Catherine Brun",

booktitle = "Actes de la conf{\'e}rence TOTh 2019",

url = "http://toth.condillac.org/ttm-2019",

}

Ramos, M , Costa, R & Roche, CBJ-J 2020, Dealing with specialized co-text in text mining: the verbal terminological collocations. in C Roche & C Brun (eds), Actes de la conférence TOTh 2019: Terminologie & Ontologie: Théories et Applications., 19, Terminologica, Presses Universitaires Savoie Mont Blanc, Chambéry, pp. 339-362, T.T.M. 2019 : Terminologie et Fouille de Textes, Chambéry, France, 6/06/19. <http://ontologia.fr/TOTh/Conference/TOTh2019/TOTh_2019.pdf>

Dealing with specialized co-text in text mining: the verbal terminological collocations. / Ramos, Margarida ; Costa, Rute ; Roche, Christophe Bernard Jean-Joseph.
Actes de la conférence TOTh 2019: Terminologie & Ontologie: Théories et Applications. ed. / Christophe Roche; Catherine Brun. Chambéry: Presses Universitaires Savoie Mont Blanc, 2020. p. 339-362 19 (Terminologica).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Dealing with specialized co-text in text mining

T2 - T.T.M. 2019 : Terminologie et Fouille de Textes

AU - Ramos, Margarida

AU - Costa, Rute

AU - Roche, Christophe Bernard Jean-Joseph

N1 - UIDB/03213/2020 UIDP/03213/2020 UID/LIN/03213/2019

PY - 2020/7/6

Y1 - 2020/7/6

N2 - The aim of this paper is to organise lexical and conceptual knowledge by analysing a domain-specific corpus. The domain we focus on is the cork industry. Through the analysis of the corpus, we have found that some common verbs in Portuguese, such as “choose” and “separate” acquire a specialised value in the field under study. This was the starting point for the analysis of the terminological collocations where verbs are the core constituents. For the analysis of these verbal terminological collocations, we used natural language processing techniques, building simple and complex CQL structures with RegEx. The outcome of this analysis permits us to introduce a distinction between polylexical terms and terminological collocations. The terminological collocation is a reality of great relevance in specialised discourse, but unlike terms, it is not defined by conceptual criteria, but by morphological and syntactic criteria.

AB - The aim of this paper is to organise lexical and conceptual knowledge by analysing a domain-specific corpus. The domain we focus on is the cork industry. Through the analysis of the corpus, we have found that some common verbs in Portuguese, such as “choose” and “separate” acquire a specialised value in the field under study. This was the starting point for the analysis of the terminological collocations where verbs are the core constituents. For the analysis of these verbal terminological collocations, we used natural language processing techniques, building simple and complex CQL structures with RegEx. The outcome of this analysis permits us to introduce a distinction between polylexical terms and terminological collocations. The terminological collocation is a reality of great relevance in specialised discourse, but unlike terms, it is not defined by conceptual criteria, but by morphological and syntactic criteria.

KW - Text mining

KW - Terminology

KW - Lexicography

KW - Collocation

KW - Compounding

KW - Definition

KW - Natural language processing

KW - Verbal terminological collocation

M3 - Conference contribution

SN - 978-2-919732-80-7

T3 - Terminologica

SP - 339

EP - 362

BT - Actes de la conférence TOTh 2019

A2 - Roche, Christophe

A2 - Brun, Catherine

PB - Presses Universitaires Savoie Mont Blanc

CY - Chambéry

Y2 - 6 June 2019 through 7 June 2019

ER -

Dealing with specialized co-text in text mining: the verbal terminological collocations

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Prizes

Doctoral Scholarship

Activities

Dealing with specialized co-text in text mining: The verbal terminological collocations

T.T.M. 2019 : Terminologie et Fouille de Textes

Cite this