@inproceedings{nazar-lindemann-2022-terminology,
title = "Terminology extraction using co-occurrence patterns as predictors of semantic relevance",
author = "Nazar, Rogelio and
Lindemann, David",
editor = "Costa, Rute and
Carvalho, Sara and
Ani{\'c}, Ana Ostro{\v{s}}ki and
Khan, Anas Fahad",
booktitle = "Proceedings of the Workshop on Terminology in the 21st century: many faces, many places",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.term-1.5",
pages = "26--29",
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.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nazar-lindemann-2022-terminology">
<titleInfo>
<title>Terminology extraction using co-occurrence patterns as predictors of semantic relevance</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rogelio</namePart>
<namePart type="family">Nazar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Lindemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Workshop on Terminology in the 21st century: many faces, many places</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rute</namePart>
<namePart type="family">Costa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Carvalho</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ana</namePart>
<namePart type="given">Ostroški</namePart>
<namePart type="family">Anić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anas</namePart>
<namePart type="given">Fahad</namePart>
<namePart type="family">Khan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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.</abstract>
<identifier type="citekey">nazar-lindemann-2022-terminology</identifier>
<location>
<url>https://aclanthology.org/2022.term-1.5</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>26</start>
<end>29</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Terminology extraction using co-occurrence patterns as predictors of semantic relevance
%A Nazar, Rogelio
%A Lindemann, David
%Y Costa, Rute
%Y Carvalho, Sara
%Y Anić, Ana Ostroški
%Y Khan, Anas Fahad
%S Proceedings of the Workshop on Terminology in the 21st century: many faces, many places
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F nazar-lindemann-2022-terminology
%X 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.
%U https://aclanthology.org/2022.term-1.5
%P 26-29
Markdown (Informal)
[Terminology extraction using co-occurrence patterns as predictors of semantic relevance](https://aclanthology.org/2022.term-1.5) (Nazar & Lindemann, TERM 2022)
ACL