@inproceedings{sajatovic-etal-2019-evaluating,
title = "Evaluating Automatic Term Extraction Methods on Individual Documents",
author = "{\v{S}}ajatovi{\'c}, Antonio and
Buljan, Maja and
{\v{S}}najder, Jan and
Dalbelo Ba{\v{s}}i{\'c}, Bojana",
booktitle = "Proceedings of the Joint Workshop on Multiword Expressions and WordNet (MWE-WN 2019)",
month = aug,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-5118",
doi = "10.18653/v1/W19-5118",
pages = "149--154",
abstract = "Automatic Term Extraction (ATE) extracts terminology from domain-specific corpora. ATE is used in many NLP tasks, including Computer Assisted Translation, where it is typically applied to individual documents rather than the entire corpus. While corpus-level ATE has been extensively evaluated, it is not obvious how the results transfer to document-level ATE. To fill this gap, we evaluate 16 state-of-the-art ATE methods on full-length documents from three different domains, on both corpus and document levels. Unlike existing studies, our evaluation is more realistic as we take into account all gold terms. We show that no single method is best in corpus-level ATE, but C-Value and KeyConceptRelatendess surpass others in document-level ATE.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sajatovic-etal-2019-evaluating">
<titleInfo>
<title>Evaluating Automatic Term Extraction Methods on Individual Documents</title>
</titleInfo>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Šajatović</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maja</namePart>
<namePart type="family">Buljan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Šnajder</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bojana</namePart>
<namePart type="family">Dalbelo Bašić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-aug</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Joint Workshop on Multiword Expressions and WordNet (MWE-WN 2019)</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Florence, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Automatic Term Extraction (ATE) extracts terminology from domain-specific corpora. ATE is used in many NLP tasks, including Computer Assisted Translation, where it is typically applied to individual documents rather than the entire corpus. While corpus-level ATE has been extensively evaluated, it is not obvious how the results transfer to document-level ATE. To fill this gap, we evaluate 16 state-of-the-art ATE methods on full-length documents from three different domains, on both corpus and document levels. Unlike existing studies, our evaluation is more realistic as we take into account all gold terms. We show that no single method is best in corpus-level ATE, but C-Value and KeyConceptRelatendess surpass others in document-level ATE.</abstract>
<identifier type="citekey">sajatovic-etal-2019-evaluating</identifier>
<identifier type="doi">10.18653/v1/W19-5118</identifier>
<location>
<url>https://aclanthology.org/W19-5118</url>
</location>
<part>
<date>2019-aug</date>
<extent unit="page">
<start>149</start>
<end>154</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evaluating Automatic Term Extraction Methods on Individual Documents
%A Šajatović, Antonio
%A Buljan, Maja
%A Šnajder, Jan
%A Dalbelo Bašić, Bojana
%S Proceedings of the Joint Workshop on Multiword Expressions and WordNet (MWE-WN 2019)
%D 2019
%8 aug
%I Association for Computational Linguistics
%C Florence, Italy
%F sajatovic-etal-2019-evaluating
%X Automatic Term Extraction (ATE) extracts terminology from domain-specific corpora. ATE is used in many NLP tasks, including Computer Assisted Translation, where it is typically applied to individual documents rather than the entire corpus. While corpus-level ATE has been extensively evaluated, it is not obvious how the results transfer to document-level ATE. To fill this gap, we evaluate 16 state-of-the-art ATE methods on full-length documents from three different domains, on both corpus and document levels. Unlike existing studies, our evaluation is more realistic as we take into account all gold terms. We show that no single method is best in corpus-level ATE, but C-Value and KeyConceptRelatendess surpass others in document-level ATE.
%R 10.18653/v1/W19-5118
%U https://aclanthology.org/W19-5118
%U https://doi.org/10.18653/v1/W19-5118
%P 149-154
Markdown (Informal)
[Evaluating Automatic Term Extraction Methods on Individual Documents](https://aclanthology.org/W19-5118) (Šajatović et al., 2019)
ACL