@inproceedings{oliver-vazquez-2020-termeval,
title = "{T}erm{E}val 2020: Using {TSR} Filtering Method to Improve Automatic Term Extraction",
author = "Oliver, Antoni and
V{\`a}zquez, Merc{\`e}",
editor = "Daille, B{\'e}atrice and
Kageura, Kyo and
Terryn, Ayla Rigouts",
booktitle = "Proceedings of the 6th International Workshop on Computational Terminology",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.computerm-1.15",
pages = "106--113",
abstract = "The identification of terms from domain-specific corpora using computational methods is a highly time-consuming task because terms has to be validated by specialists. In order to improve term candidate selection, we have developed the Token Slot Recognition (TSR) method, a filtering strategy based on terminological tokens which is used to rank extracted term candidates from domain-specific corpora. We have implemented this filtering strategy in TBXTools. In this paper we present the system we have used in the TermEval 2020 shared task on monolingual term extraction. We also present the evaluation results for the system for English, French and Dutch and for two corpora: corruption and heart failure. For English and French we have used a linguistic methodology based on POS patterns, and for Dutch we have used a statistical methodology based on n-grams calculation and filtering with stop-words. For all languages, TSR (Token Slot Recognition) filtering method has been applied. We have obtained competitive results, but there is still room for improvement of the system.",
language = "English",
ISBN = "979-10-95546-57-3",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="oliver-vazquez-2020-termeval">
<titleInfo>
<title>TermEval 2020: Using TSR Filtering Method to Improve Automatic Term Extraction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Antoni</namePart>
<namePart type="family">Oliver</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mercè</namePart>
<namePart type="family">Vàzquez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 6th International Workshop on Computational Terminology</title>
</titleInfo>
<name type="personal">
<namePart type="given">Béatrice</namePart>
<namePart type="family">Daille</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kyo</namePart>
<namePart type="family">Kageura</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>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-57-3</identifier>
</relatedItem>
<abstract>The identification of terms from domain-specific corpora using computational methods is a highly time-consuming task because terms has to be validated by specialists. In order to improve term candidate selection, we have developed the Token Slot Recognition (TSR) method, a filtering strategy based on terminological tokens which is used to rank extracted term candidates from domain-specific corpora. We have implemented this filtering strategy in TBXTools. In this paper we present the system we have used in the TermEval 2020 shared task on monolingual term extraction. We also present the evaluation results for the system for English, French and Dutch and for two corpora: corruption and heart failure. For English and French we have used a linguistic methodology based on POS patterns, and for Dutch we have used a statistical methodology based on n-grams calculation and filtering with stop-words. For all languages, TSR (Token Slot Recognition) filtering method has been applied. We have obtained competitive results, but there is still room for improvement of the system.</abstract>
<identifier type="citekey">oliver-vazquez-2020-termeval</identifier>
<location>
<url>https://aclanthology.org/2020.computerm-1.15</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>106</start>
<end>113</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TermEval 2020: Using TSR Filtering Method to Improve Automatic Term Extraction
%A Oliver, Antoni
%A Vàzquez, Mercè
%Y Daille, Béatrice
%Y Kageura, Kyo
%Y Terryn, Ayla Rigouts
%S Proceedings of the 6th International Workshop on Computational Terminology
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-57-3
%G English
%F oliver-vazquez-2020-termeval
%X The identification of terms from domain-specific corpora using computational methods is a highly time-consuming task because terms has to be validated by specialists. In order to improve term candidate selection, we have developed the Token Slot Recognition (TSR) method, a filtering strategy based on terminological tokens which is used to rank extracted term candidates from domain-specific corpora. We have implemented this filtering strategy in TBXTools. In this paper we present the system we have used in the TermEval 2020 shared task on monolingual term extraction. We also present the evaluation results for the system for English, French and Dutch and for two corpora: corruption and heart failure. For English and French we have used a linguistic methodology based on POS patterns, and for Dutch we have used a statistical methodology based on n-grams calculation and filtering with stop-words. For all languages, TSR (Token Slot Recognition) filtering method has been applied. We have obtained competitive results, but there is still room for improvement of the system.
%U https://aclanthology.org/2020.computerm-1.15
%P 106-113
Markdown (Informal)
[TermEval 2020: Using TSR Filtering Method to Improve Automatic Term Extraction](https://aclanthology.org/2020.computerm-1.15) (Oliver & Vàzquez, CompuTerm 2020)
ACL