@inproceedings{vitas-etal-2016-differentiate,
title = "How to Differentiate the Closely Related Standard Languages?",
author = "Vitas, Du{\v{s}}ko and
Popovi{\'c}, Ljubomir and
Krstev, Cvetana and
Ze{\v{c}}evi{\'c}, An{\dj}elka",
booktitle = "Proceedings of the Second International Conference on Computational Linguistics in Bulgaria (CLIB 2016)",
month = sep,
year = "2016",
address = "Sofia, Bulgaria",
publisher = "Department of Computational Linguistics, Institute for Bulgarian Language, Bulgarian Academy of Sciences",
url = "https://aclanthology.org/2016.clib-1.1",
pages = "1--10",
abstract = "In this paper the adequacy of the SETimes corpus as a basis for the comparison of closely related languages that are used in countries that emerged after the breakup of Yugoslavia is discussed by comparing it with other corpora. It is shown that the phenomena observed in this corpus and used to illustrate differences most specifically between Serbian and Croatian are consistent neither with their standards nor with other sources. Thus, results obtained on the basis of the SETimes corpus are corpus-biased and have to be reconsidered. This proves that the size of a corpus and its composition used in a linguistic research are crucial for assessing the obtained results.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vitas-etal-2016-differentiate">
<titleInfo>
<title>How to Differentiate the Closely Related Standard Languages?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Duško</namePart>
<namePart type="family">Vitas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ljubomir</namePart>
<namePart type="family">Popović</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cvetana</namePart>
<namePart type="family">Krstev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anđelka</namePart>
<namePart type="family">Zečević</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second International Conference on Computational Linguistics in Bulgaria (CLIB 2016)</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>In this paper the adequacy of the SETimes corpus as a basis for the comparison of closely related languages that are used in countries that emerged after the breakup of Yugoslavia is discussed by comparing it with other corpora. It is shown that the phenomena observed in this corpus and used to illustrate differences most specifically between Serbian and Croatian are consistent neither with their standards nor with other sources. Thus, results obtained on the basis of the SETimes corpus are corpus-biased and have to be reconsidered. This proves that the size of a corpus and its composition used in a linguistic research are crucial for assessing the obtained results.</abstract>
<identifier type="citekey">vitas-etal-2016-differentiate</identifier>
<location>
<url>https://aclanthology.org/2016.clib-1.1</url>
</location>
<part>
<date>2016-09</date>
<extent unit="page">
<start>1</start>
<end>10</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T How to Differentiate the Closely Related Standard Languages?
%A Vitas, Duško
%A Popović, Ljubomir
%A Krstev, Cvetana
%A Zečević, Anđelka
%S Proceedings of the Second International Conference on Computational Linguistics in Bulgaria (CLIB 2016)
%D 2016
%8 September
%I Department of Computational Linguistics, Institute for Bulgarian Language, Bulgarian Academy of Sciences
%C Sofia, Bulgaria
%F vitas-etal-2016-differentiate
%X In this paper the adequacy of the SETimes corpus as a basis for the comparison of closely related languages that are used in countries that emerged after the breakup of Yugoslavia is discussed by comparing it with other corpora. It is shown that the phenomena observed in this corpus and used to illustrate differences most specifically between Serbian and Croatian are consistent neither with their standards nor with other sources. Thus, results obtained on the basis of the SETimes corpus are corpus-biased and have to be reconsidered. This proves that the size of a corpus and its composition used in a linguistic research are crucial for assessing the obtained results.
%U https://aclanthology.org/2016.clib-1.1
%P 1-10
Markdown (Informal)
[How to Differentiate the Closely Related Standard Languages?](https://aclanthology.org/2016.clib-1.1) (Vitas et al., CLIB 2016)
ACL
- Duško Vitas, Ljubomir Popović, Cvetana Krstev, and Anđelka Zečević. 2016. How to Differentiate the Closely Related Standard Languages?. In Proceedings of the Second International Conference on Computational Linguistics in Bulgaria (CLIB 2016), pages 1–10, Sofia, Bulgaria. Department of Computational Linguistics, Institute for Bulgarian Language, Bulgarian Academy of Sciences.