@inproceedings{vazquez-etal-2026-comparative,
title = "A Comparative Study in Corpus Linguistics Applied to Automatic Terminology Extraction",
author = "V{\`a}zquez, Merc{\`e} and
Alvarez-Vidal, Sergi and
Oliver, Antoni",
editor = "Rapp, Reinhard and
Terryn, Ayla Rigouts and
Sharoff, Serge and
Zweigenbaum, Pierre",
booktitle = "Proceedings of the 19th Workshop on Building and Using Comparable Corpora ({BUCC})",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.bucc-1.4/",
doi = "10.63317/2u8zp4nujj25",
pages = "20--29",
abstract = "Parallel and comparable corpora are the main linguistic resources to identify multilingual terminology using automatic term extraction tools. However, parallel corpora are available only for certain languages, domains and genres, and comparable corpora have some limitations when identifying corresponding terms. To implement a more efficient selection of multilingual terminology, we compared the performance of using specialised parallel and comparable corpora applied to languages with various forms of capital in linguistic resources. This paper presents a comparative study in corpus linguistics in which we automatically identify terms in Catalan, Spanish and English in legislation and administrative law using parallel corpora, comparable corpora and a combined methodology based on both typologies of corpora together with word embeddings. We observe that the combined methodology implemented obtains a higher number of term candidates than when working exclusively with parallel or comparable corpora. The evaluation of the results is performed using a terminological thesaurus as a gold standard. The new methodology presented in our study permits us to identify multilingual terminology in an efficient way, especially in Catalan-Spanish languages."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vazquez-etal-2026-comparative">
<titleInfo>
<title>A Comparative Study in Corpus Linguistics Applied to Automatic Terminology Extraction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mercè</namePart>
<namePart type="family">Vàzquez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sergi</namePart>
<namePart type="family">Alvarez-Vidal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antoni</namePart>
<namePart type="family">Oliver</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 19th Workshop on Building and Using Comparable Corpora (BUCC)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Reinhard</namePart>
<namePart type="family">Rapp</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayla</namePart>
<namePart type="given">Rigouts</namePart>
<namePart type="family">Terryn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Serge</namePart>
<namePart type="family">Sharoff</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pierre</namePart>
<namePart type="family">Zweigenbaum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Parallel and comparable corpora are the main linguistic resources to identify multilingual terminology using automatic term extraction tools. However, parallel corpora are available only for certain languages, domains and genres, and comparable corpora have some limitations when identifying corresponding terms. To implement a more efficient selection of multilingual terminology, we compared the performance of using specialised parallel and comparable corpora applied to languages with various forms of capital in linguistic resources. This paper presents a comparative study in corpus linguistics in which we automatically identify terms in Catalan, Spanish and English in legislation and administrative law using parallel corpora, comparable corpora and a combined methodology based on both typologies of corpora together with word embeddings. We observe that the combined methodology implemented obtains a higher number of term candidates than when working exclusively with parallel or comparable corpora. The evaluation of the results is performed using a terminological thesaurus as a gold standard. The new methodology presented in our study permits us to identify multilingual terminology in an efficient way, especially in Catalan-Spanish languages.</abstract>
<identifier type="citekey">vazquez-etal-2026-comparative</identifier>
<identifier type="doi">10.63317/2u8zp4nujj25</identifier>
<location>
<url>https://aclanthology.org/2026.bucc-1.4/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>20</start>
<end>29</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Comparative Study in Corpus Linguistics Applied to Automatic Terminology Extraction
%A Vàzquez, Mercè
%A Alvarez-Vidal, Sergi
%A Oliver, Antoni
%Y Rapp, Reinhard
%Y Terryn, Ayla Rigouts
%Y Sharoff, Serge
%Y Zweigenbaum, Pierre
%S Proceedings of the 19th Workshop on Building and Using Comparable Corpora (BUCC)
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma de Mallorca, Spain
%F vazquez-etal-2026-comparative
%X Parallel and comparable corpora are the main linguistic resources to identify multilingual terminology using automatic term extraction tools. However, parallel corpora are available only for certain languages, domains and genres, and comparable corpora have some limitations when identifying corresponding terms. To implement a more efficient selection of multilingual terminology, we compared the performance of using specialised parallel and comparable corpora applied to languages with various forms of capital in linguistic resources. This paper presents a comparative study in corpus linguistics in which we automatically identify terms in Catalan, Spanish and English in legislation and administrative law using parallel corpora, comparable corpora and a combined methodology based on both typologies of corpora together with word embeddings. We observe that the combined methodology implemented obtains a higher number of term candidates than when working exclusively with parallel or comparable corpora. The evaluation of the results is performed using a terminological thesaurus as a gold standard. The new methodology presented in our study permits us to identify multilingual terminology in an efficient way, especially in Catalan-Spanish languages.
%R 10.63317/2u8zp4nujj25
%U https://aclanthology.org/2026.bucc-1.4/
%U https://doi.org/10.63317/2u8zp4nujj25
%P 20-29
Markdown (Informal)
[A Comparative Study in Corpus Linguistics Applied to Automatic Terminology Extraction](https://aclanthology.org/2026.bucc-1.4/) (Vàzquez et al., BUCC 2026)
ACL