@inproceedings{08900298be9449249b71b5a137911922,
title = "Terminology extraction using co-occurrence patterns as predictors of semantic relevance",
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.",
keywords = "co-occurrence patterns, semantic relevance, terminology extraction",
author = "Rogelio Nazar and David Lindemann",
note = "Publisher Copyright: {\textcopyright} European Language Resources Association (ELRA), licensed under CC-BY-NC-4.0.; Terminology in the 21st Century: Many Faces, Many Places, Term 2022 ; Conference date: 20-06-2022",
year = "2022",
language = "English",
series = "Terminology 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",
publisher = "European Language Resources Association (ELRA)",
pages = "26--29",
editor = "Rute Costa and Sara Carvalho and Anic, {Ana Ostroski} and Khan, {Anas Fahad}",
booktitle = "Terminology in the 21st Century",
}