@inproceedings{priban-steinberger-2022-czech,
title = "{C}zech Dataset for Cross-lingual Subjectivity Classification",
author = "P{\v{r}}ib{\'a}{\v{n}}, Pavel and
Steinberger, Josef",
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
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.148",
pages = "1381--1391",
abstract = "In this paper, we introduce a new Czech subjectivity dataset of 10k manually annotated subjective and objective sentences from movie reviews and descriptions. Our prime motivation is to provide a reliable dataset that can be used with the existing English dataset as a benchmark to test the ability of pre-trained multilingual models to transfer knowledge between Czech and English and vice versa. Two annotators annotated the dataset reaching 0.83 of the Cohen{'}s K inter-annotator agreement. To the best of our knowledge, this is the first subjectivity dataset for the Czech language. We also created an additional dataset that consists of 200k automatically labeled sentences. Both datasets are freely available for research purposes. Furthermore, we fine-tune five pre-trained BERT-like models to set a monolingual baseline for the new dataset and we achieve 93.56{\%} of accuracy. We fine-tune models on the existing English dataset for which we obtained results that are on par with the current state-of-the-art results. Finally, we perform zero-shot cross-lingual subjectivity classification between Czech and English to verify the usability of our dataset as the cross-lingual benchmark. We compare and discuss the cross-lingual and monolingual results and the ability of multilingual models to transfer knowledge between languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="priban-steinberger-2022-czech">
<titleInfo>
<title>Czech Dataset for Cross-lingual Subjectivity Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pavel</namePart>
<namePart type="family">Přibáň</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Josef</namePart>
<namePart type="family">Steinberger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth 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">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>
</relatedItem>
<abstract>In this paper, we introduce a new Czech subjectivity dataset of 10k manually annotated subjective and objective sentences from movie reviews and descriptions. Our prime motivation is to provide a reliable dataset that can be used with the existing English dataset as a benchmark to test the ability of pre-trained multilingual models to transfer knowledge between Czech and English and vice versa. Two annotators annotated the dataset reaching 0.83 of the Cohen’s K inter-annotator agreement. To the best of our knowledge, this is the first subjectivity dataset for the Czech language. We also created an additional dataset that consists of 200k automatically labeled sentences. Both datasets are freely available for research purposes. Furthermore, we fine-tune five pre-trained BERT-like models to set a monolingual baseline for the new dataset and we achieve 93.56% of accuracy. We fine-tune models on the existing English dataset for which we obtained results that are on par with the current state-of-the-art results. Finally, we perform zero-shot cross-lingual subjectivity classification between Czech and English to verify the usability of our dataset as the cross-lingual benchmark. We compare and discuss the cross-lingual and monolingual results and the ability of multilingual models to transfer knowledge between languages.</abstract>
<identifier type="citekey">priban-steinberger-2022-czech</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.148</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>1381</start>
<end>1391</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Czech Dataset for Cross-lingual Subjectivity Classification
%A Přibáň, Pavel
%A Steinberger, Josef
%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 Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F priban-steinberger-2022-czech
%X In this paper, we introduce a new Czech subjectivity dataset of 10k manually annotated subjective and objective sentences from movie reviews and descriptions. Our prime motivation is to provide a reliable dataset that can be used with the existing English dataset as a benchmark to test the ability of pre-trained multilingual models to transfer knowledge between Czech and English and vice versa. Two annotators annotated the dataset reaching 0.83 of the Cohen’s K inter-annotator agreement. To the best of our knowledge, this is the first subjectivity dataset for the Czech language. We also created an additional dataset that consists of 200k automatically labeled sentences. Both datasets are freely available for research purposes. Furthermore, we fine-tune five pre-trained BERT-like models to set a monolingual baseline for the new dataset and we achieve 93.56% of accuracy. We fine-tune models on the existing English dataset for which we obtained results that are on par with the current state-of-the-art results. Finally, we perform zero-shot cross-lingual subjectivity classification between Czech and English to verify the usability of our dataset as the cross-lingual benchmark. We compare and discuss the cross-lingual and monolingual results and the ability of multilingual models to transfer knowledge between languages.
%U https://aclanthology.org/2022.lrec-1.148
%P 1381-1391
Markdown (Informal)
[Czech Dataset for Cross-lingual Subjectivity Classification](https://aclanthology.org/2022.lrec-1.148) (Přibáň & Steinberger, LREC 2022)
ACL