@inproceedings{rituma-etal-2024-classifying,
title = "Classifying Multi{--}Word Expressions in the {L}atvian Monolingual Electronic Dictionary T{\={e}}zaurs.lv",
author = "Rituma, Laura and
Ne{\v{s}}pore-B{\={e}}rzkalne, Gunta and
Klints, Agute and
Lokmane, Ilze and
St{\={a}}de, Madara and
Paikens, P{\={e}}teris",
booktitle = "Proceedings of the Sixth International Conference on Computational Linguistics in Bulgaria (CLIB 2024)",
month = sep,
year = "2024",
address = "Sofia, Bulgaria",
publisher = "Department of Computational Linguistics, Institute for Bulgarian Language, Bulgarian Academy of Sciences",
url = "https://aclanthology.org/2024.clib-1.11/",
pages = "113--118",
abstract = "The electronic dictionary T{\={e}}zaurs.lv contains more than 400,000 entries from which 73,000 entries are multi-word expressions (MWEs). Over the past two years, there has been an ongoing division of these MWEs into subgroups (proper names, multi-word terms, taxa, phraseological units, collocations). The article describes the classification of MWEs, focusing on phraseological units (approximately 7,250 entries), as well as on borderline cases of phraseological unit types (phrasemes and idioms) and different MWE groups in general. The division of phraseological units depends on semantic divisibility and figurativeness. In a phraseme, at least one of the constituents retains its literal sense, whereas the meaning of an idiom is not dependent on the literal sense of any of its constituents. As a result, 65919 entries of MWE have been manually classified, and now this information of MWE type is available for the users of the electronic dictionary T{\={e}}zaurs.lv."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rituma-etal-2024-classifying">
<titleInfo>
<title>Classifying Multi–Word Expressions in the Latvian Monolingual Electronic Dictionary Tēzaurs.lv</title>
</titleInfo>
<name type="personal">
<namePart type="given">Laura</namePart>
<namePart type="family">Rituma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gunta</namePart>
<namePart type="family">Nešpore-Bērzkalne</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Agute</namePart>
<namePart type="family">Klints</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ilze</namePart>
<namePart type="family">Lokmane</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Madara</namePart>
<namePart type="family">Stāde</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pēteris</namePart>
<namePart type="family">Paikens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth International Conference on Computational Linguistics in Bulgaria (CLIB 2024)</title>
</titleInfo>
<originInfo>
<publisher>Department of Computational Linguistics, Institute for Bulgarian Language, Bulgarian Academy of Sciences</publisher>
<place>
<placeTerm type="text">Sofia, Bulgaria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The electronic dictionary Tēzaurs.lv contains more than 400,000 entries from which 73,000 entries are multi-word expressions (MWEs). Over the past two years, there has been an ongoing division of these MWEs into subgroups (proper names, multi-word terms, taxa, phraseological units, collocations). The article describes the classification of MWEs, focusing on phraseological units (approximately 7,250 entries), as well as on borderline cases of phraseological unit types (phrasemes and idioms) and different MWE groups in general. The division of phraseological units depends on semantic divisibility and figurativeness. In a phraseme, at least one of the constituents retains its literal sense, whereas the meaning of an idiom is not dependent on the literal sense of any of its constituents. As a result, 65919 entries of MWE have been manually classified, and now this information of MWE type is available for the users of the electronic dictionary Tēzaurs.lv.</abstract>
<identifier type="citekey">rituma-etal-2024-classifying</identifier>
<location>
<url>https://aclanthology.org/2024.clib-1.11/</url>
</location>
<part>
<date>2024-09</date>
<extent unit="page">
<start>113</start>
<end>118</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Classifying Multi–Word Expressions in the Latvian Monolingual Electronic Dictionary Tēzaurs.lv
%A Rituma, Laura
%A Nešpore-Bērzkalne, Gunta
%A Klints, Agute
%A Lokmane, Ilze
%A Stāde, Madara
%A Paikens, Pēteris
%S Proceedings of the Sixth International Conference on Computational Linguistics in Bulgaria (CLIB 2024)
%D 2024
%8 September
%I Department of Computational Linguistics, Institute for Bulgarian Language, Bulgarian Academy of Sciences
%C Sofia, Bulgaria
%F rituma-etal-2024-classifying
%X The electronic dictionary Tēzaurs.lv contains more than 400,000 entries from which 73,000 entries are multi-word expressions (MWEs). Over the past two years, there has been an ongoing division of these MWEs into subgroups (proper names, multi-word terms, taxa, phraseological units, collocations). The article describes the classification of MWEs, focusing on phraseological units (approximately 7,250 entries), as well as on borderline cases of phraseological unit types (phrasemes and idioms) and different MWE groups in general. The division of phraseological units depends on semantic divisibility and figurativeness. In a phraseme, at least one of the constituents retains its literal sense, whereas the meaning of an idiom is not dependent on the literal sense of any of its constituents. As a result, 65919 entries of MWE have been manually classified, and now this information of MWE type is available for the users of the electronic dictionary Tēzaurs.lv.
%U https://aclanthology.org/2024.clib-1.11/
%P 113-118
Markdown (Informal)
[Classifying Multi–Word Expressions in the Latvian Monolingual Electronic Dictionary Tēzaurs.lv](https://aclanthology.org/2024.clib-1.11/) (Rituma et al., CLIB 2024)
ACL
- Laura Rituma, Gunta Nešpore-Bērzkalne, Agute Klints, Ilze Lokmane, Madara Stāde, and Pēteris Paikens. 2024. Classifying Multi–Word Expressions in the Latvian Monolingual Electronic Dictionary Tēzaurs.lv. In Proceedings of the Sixth International Conference on Computational Linguistics in Bulgaria (CLIB 2024), pages 113–118, Sofia, Bulgaria. Department of Computational Linguistics, Institute for Bulgarian Language, Bulgarian Academy of Sciences.