Terminology extraction using co-occurrence patterns as predictors of semantic relevance

Rogelio Nazar, David Lindemann

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

We propose a method for automatic term extraction based on a statistical measure that ranks term candidates according to their semantic relevance to a specialised domain. As a measure of relevance we use term co-occurrence, defined as the repeated instantiation of two terms in the same sentences, in indifferent order and at variable distances. In this way, term candidates are ranked higher if they show a tendency to co-occur with a selected group of other units, as opposed to those showing more uniform distributions. No external resources are needed for the application of the method, but performance improves when provided with a pre-existing term list. We present results of the application of this method to a Spanish-English Linguistics corpus, and the evaluation compares favourably with a standard method based on reference corpora.

Original languageEnglish
Title of host publicationTerminology in the 21st Century
Subtitle of host publicationMany Faces, Many Places, Term 2022 - held in conjunction with the International Conference on Language Resources and Evaluation, LREC 2022 - Proceedings
EditorsRute Costa, Sara Carvalho, Ana Ostroski Anic, Anas Fahad Khan
PublisherEuropean Language Resources Association (ELRA)
Pages26-29
Number of pages4
ISBN (Electronic)9791095546955
StatePublished - 2022
EventTerminology in the 21st Century: Many Faces, Many Places, Term 2022 - Marseille, France
Duration: 20 Jun 2022 → …

Publication series

NameTerminology in the 21st Century: Many Faces, Many Places, Term 2022 - held in conjunction with the International Conference on Language Resources and Evaluation, LREC 2022 - Proceedings

Conference

ConferenceTerminology in the 21st Century: Many Faces, Many Places, Term 2022
Country/TerritoryFrance
CityMarseille
Period20/06/22 → …

Keywords

  • co-occurrence patterns
  • semantic relevance
  • terminology extraction

Fingerprint

Dive into the research topics of 'Terminology extraction using co-occurrence patterns as predictors of semantic relevance'. Together they form a unique fingerprint.

Cite this