@inproceedings{dmitrieva-2023-automatic,
title = "Automatic text simplification of {R}ussian texts using control tokens",
author = "Dmitrieva, Anna",
editor = "Piskorski, Jakub and
Marci{\'n}czuk, Micha{\l} and
Nakov, Preslav and
Ogrodniczuk, Maciej and
Pollak, Senja and
P{\v{r}}ib{\'a}{\v{n}}, Pavel and
Rybak, Piotr and
Steinberger, Josef and
Yangarber, Roman",
booktitle = "Proceedings of the 9th Workshop on Slavic Natural Language Processing 2023 (SlavicNLP 2023)",
month = may,
year = "2023",
address = "Dubrovnik, Croatia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.bsnlp-1.9",
doi = "10.18653/v1/2023.bsnlp-1.9",
pages = "70--77",
abstract = "This paper describes the research on the possibilities to control automatic text simplification with special tokens that allow modifying the length, paraphrasing degree, syntactic complexity, and the CEFR (Common European Framework of Reference) grade level of the output texts, i.e. the level of language proficiency a non-native speaker would need to understand them. The project is focused on Russian texts and aims to continue and broaden the existing research on controlled Russian text simplification. It is done by exploring available datasets for monolingual Russian machine translation (paraphrasing and simplification), experimenting with various model architectures, and adding control tokens that have not been used on Russian texts previously.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dmitrieva-2023-automatic">
<titleInfo>
<title>Automatic text simplification of Russian texts using control tokens</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Dmitrieva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 9th Workshop on Slavic Natural Language Processing 2023 (SlavicNLP 2023)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jakub</namePart>
<namePart type="family">Piskorski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michał</namePart>
<namePart type="family">Marcińczuk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maciej</namePart>
<namePart type="family">Ogrodniczuk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Senja</namePart>
<namePart type="family">Pollak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pavel</namePart>
<namePart type="family">Přibáň</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Piotr</namePart>
<namePart type="family">Rybak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Josef</namePart>
<namePart type="family">Steinberger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roman</namePart>
<namePart type="family">Yangarber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dubrovnik, Croatia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes the research on the possibilities to control automatic text simplification with special tokens that allow modifying the length, paraphrasing degree, syntactic complexity, and the CEFR (Common European Framework of Reference) grade level of the output texts, i.e. the level of language proficiency a non-native speaker would need to understand them. The project is focused on Russian texts and aims to continue and broaden the existing research on controlled Russian text simplification. It is done by exploring available datasets for monolingual Russian machine translation (paraphrasing and simplification), experimenting with various model architectures, and adding control tokens that have not been used on Russian texts previously.</abstract>
<identifier type="citekey">dmitrieva-2023-automatic</identifier>
<identifier type="doi">10.18653/v1/2023.bsnlp-1.9</identifier>
<location>
<url>https://aclanthology.org/2023.bsnlp-1.9</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>70</start>
<end>77</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automatic text simplification of Russian texts using control tokens
%A Dmitrieva, Anna
%Y Piskorski, Jakub
%Y Marcińczuk, Michał
%Y Nakov, Preslav
%Y Ogrodniczuk, Maciej
%Y Pollak, Senja
%Y Přibáň, Pavel
%Y Rybak, Piotr
%Y Steinberger, Josef
%Y Yangarber, Roman
%S Proceedings of the 9th Workshop on Slavic Natural Language Processing 2023 (SlavicNLP 2023)
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F dmitrieva-2023-automatic
%X This paper describes the research on the possibilities to control automatic text simplification with special tokens that allow modifying the length, paraphrasing degree, syntactic complexity, and the CEFR (Common European Framework of Reference) grade level of the output texts, i.e. the level of language proficiency a non-native speaker would need to understand them. The project is focused on Russian texts and aims to continue and broaden the existing research on controlled Russian text simplification. It is done by exploring available datasets for monolingual Russian machine translation (paraphrasing and simplification), experimenting with various model architectures, and adding control tokens that have not been used on Russian texts previously.
%R 10.18653/v1/2023.bsnlp-1.9
%U https://aclanthology.org/2023.bsnlp-1.9
%U https://doi.org/10.18653/v1/2023.bsnlp-1.9
%P 70-77
Markdown (Informal)
[Automatic text simplification of Russian texts using control tokens](https://aclanthology.org/2023.bsnlp-1.9) (Dmitrieva, BSNLP 2023)
ACL