@inproceedings{cinkova-rybicki-2020-stylometry,
title = "Stylometry in a Bilingual Setup",
author = "Cinkova, Silvie and
Rybicki, Jan",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.123",
pages = "977--984",
abstract = "The method of stylometry by most frequent words does not allow direct comparison of original texts and their translations, i.e. across languages. For instance, in a bilingual Czech-German text collection containing parallel texts (originals and translations in both directions, along with Czech and German translations from other languages), authors would not cluster across languages, since frequency word lists for any Czech texts are obviously going to be more similar to each other than to a German text, and the other way round. We have tried to come up with an interlingua that would remove the language-specific features and possibly keep the linguistically independent features of individual author signal, if they exist. We have tagged, lemmatized, and parsed each language counterpart with the corresponding language model in UDPipe, which provides a linguistic markup that is cross-lingual to a significant extent. We stripped the output of language-dependent items, but that alone did not help much. As a next step, we transformed the lemmas of both language counterparts into shared pseudolemmas based on a very crude Czech-German glossary, with a 95.6{\%} success. We show that, for stylometric methods based on the most frequent words, we can do without translations.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cinkova-rybicki-2020-stylometry">
<titleInfo>
<title>Stylometry in a Bilingual Setup</title>
</titleInfo>
<name type="personal">
<namePart type="given">Silvie</namePart>
<namePart type="family">Cinkova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Rybicki</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 Twelfth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</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">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>The method of stylometry by most frequent words does not allow direct comparison of original texts and their translations, i.e. across languages. For instance, in a bilingual Czech-German text collection containing parallel texts (originals and translations in both directions, along with Czech and German translations from other languages), authors would not cluster across languages, since frequency word lists for any Czech texts are obviously going to be more similar to each other than to a German text, and the other way round. We have tried to come up with an interlingua that would remove the language-specific features and possibly keep the linguistically independent features of individual author signal, if they exist. We have tagged, lemmatized, and parsed each language counterpart with the corresponding language model in UDPipe, which provides a linguistic markup that is cross-lingual to a significant extent. We stripped the output of language-dependent items, but that alone did not help much. As a next step, we transformed the lemmas of both language counterparts into shared pseudolemmas based on a very crude Czech-German glossary, with a 95.6% success. We show that, for stylometric methods based on the most frequent words, we can do without translations.</abstract>
<identifier type="citekey">cinkova-rybicki-2020-stylometry</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.123</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>977</start>
<end>984</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Stylometry in a Bilingual Setup
%A Cinkova, Silvie
%A Rybicki, Jan
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F cinkova-rybicki-2020-stylometry
%X The method of stylometry by most frequent words does not allow direct comparison of original texts and their translations, i.e. across languages. For instance, in a bilingual Czech-German text collection containing parallel texts (originals and translations in both directions, along with Czech and German translations from other languages), authors would not cluster across languages, since frequency word lists for any Czech texts are obviously going to be more similar to each other than to a German text, and the other way round. We have tried to come up with an interlingua that would remove the language-specific features and possibly keep the linguistically independent features of individual author signal, if they exist. We have tagged, lemmatized, and parsed each language counterpart with the corresponding language model in UDPipe, which provides a linguistic markup that is cross-lingual to a significant extent. We stripped the output of language-dependent items, but that alone did not help much. As a next step, we transformed the lemmas of both language counterparts into shared pseudolemmas based on a very crude Czech-German glossary, with a 95.6% success. We show that, for stylometric methods based on the most frequent words, we can do without translations.
%U https://aclanthology.org/2020.lrec-1.123
%P 977-984
Markdown (Informal)
[Stylometry in a Bilingual Setup](https://aclanthology.org/2020.lrec-1.123) (Cinkova & Rybicki, LREC 2020)
ACL
- Silvie Cinkova and Jan Rybicki. 2020. Stylometry in a Bilingual Setup. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 977–984, Marseille, France. European Language Resources Association.