@inproceedings{shimorina-etal-2019-creating,
title = "Creating a Corpus for {R}ussian Data-to-Text Generation Using Neural Machine Translation and Post-Editing",
author = "Shimorina, Anastasia and
Khasanova, Elena and
Gardent, Claire",
editor = "Erjavec, Toma{\v{z}} and
Marci{\'n}czuk, Micha{\l} and
Nakov, Preslav and
Piskorski, Jakub and
Pivovarova, Lidia and
{\v{S}}najder, Jan and
Steinberger, Josef and
Yangarber, Roman",
booktitle = "Proceedings of the 7th Workshop on Balto-Slavic Natural Language Processing",
month = aug,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-3706",
doi = "10.18653/v1/W19-3706",
pages = "44--49",
abstract = "In this paper, we propose an approach for semi-automatically creating a data-to-text (D2T) corpus for Russian that can be used to learn a D2T natural language generation model. An error analysis of the output of an English-to-Russian neural machine translation system shows that 80{\%} of the automatically translated sentences contain an error and that 53{\%} of all translation errors bear on named entities (NE). We therefore focus on named entities and introduce two post-editing techniques for correcting wrongly translated NEs.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shimorina-etal-2019-creating">
<titleInfo>
<title>Creating a Corpus for Russian Data-to-Text Generation Using Neural Machine Translation and Post-Editing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anastasia</namePart>
<namePart type="family">Shimorina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elena</namePart>
<namePart type="family">Khasanova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Claire</namePart>
<namePart type="family">Gardent</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 7th Workshop on Balto-Slavic Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tomaž</namePart>
<namePart type="family">Erjavec</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">Jakub</namePart>
<namePart type="family">Piskorski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lidia</namePart>
<namePart type="family">Pivovarova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Šnajder</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">Florence, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we propose an approach for semi-automatically creating a data-to-text (D2T) corpus for Russian that can be used to learn a D2T natural language generation model. An error analysis of the output of an English-to-Russian neural machine translation system shows that 80% of the automatically translated sentences contain an error and that 53% of all translation errors bear on named entities (NE). We therefore focus on named entities and introduce two post-editing techniques for correcting wrongly translated NEs.</abstract>
<identifier type="citekey">shimorina-etal-2019-creating</identifier>
<identifier type="doi">10.18653/v1/W19-3706</identifier>
<location>
<url>https://aclanthology.org/W19-3706</url>
</location>
<part>
<date>2019-08</date>
<extent unit="page">
<start>44</start>
<end>49</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Creating a Corpus for Russian Data-to-Text Generation Using Neural Machine Translation and Post-Editing
%A Shimorina, Anastasia
%A Khasanova, Elena
%A Gardent, Claire
%Y Erjavec, Tomaž
%Y Marcińczuk, Michał
%Y Nakov, Preslav
%Y Piskorski, Jakub
%Y Pivovarova, Lidia
%Y Šnajder, Jan
%Y Steinberger, Josef
%Y Yangarber, Roman
%S Proceedings of the 7th Workshop on Balto-Slavic Natural Language Processing
%D 2019
%8 August
%I Association for Computational Linguistics
%C Florence, Italy
%F shimorina-etal-2019-creating
%X In this paper, we propose an approach for semi-automatically creating a data-to-text (D2T) corpus for Russian that can be used to learn a D2T natural language generation model. An error analysis of the output of an English-to-Russian neural machine translation system shows that 80% of the automatically translated sentences contain an error and that 53% of all translation errors bear on named entities (NE). We therefore focus on named entities and introduce two post-editing techniques for correcting wrongly translated NEs.
%R 10.18653/v1/W19-3706
%U https://aclanthology.org/W19-3706
%U https://doi.org/10.18653/v1/W19-3706
%P 44-49
Markdown (Informal)
[Creating a Corpus for Russian Data-to-Text Generation Using Neural Machine Translation and Post-Editing](https://aclanthology.org/W19-3706) (Shimorina et al., BSNLP 2019)
ACL