@inproceedings{toral-etal-2019-neural,
title = "Neural Machine Translation for {E}nglish{--}{K}azakh with Morphological Segmentation and Synthetic Data",
author = "Toral, Antonio and
Edman, Lukas and
Yeshmagambetova, Galiya and
Spenader, Jennifer",
booktitle = "Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1)",
month = aug,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-5343",
doi = "10.18653/v1/W19-5343",
pages = "386--392",
abstract = "This paper presents the systems submitted by the University of Groningen to the English{--} Kazakh language pair (both translation directions) for the WMT 2019 news translation task. We explore the potential benefits of (i) morphological segmentation (both unsupervised and rule-based), given the agglutinative nature of Kazakh, (ii) data from two additional languages (Turkish and Russian), given the scarcity of English{--}Kazakh data and (iii) synthetic data, both for the source and for the target language. Our best submissions ranked second for Kazakh→English and third for English→Kazakh in terms of the BLEU automatic evaluation metric.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="toral-etal-2019-neural">
<titleInfo>
<title>Neural Machine Translation for English–Kazakh with Morphological Segmentation and Synthetic Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lukas</namePart>
<namePart type="family">Edman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Galiya</namePart>
<namePart type="family">Yeshmagambetova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jennifer</namePart>
<namePart type="family">Spenader</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-aug</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1)</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Florence, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents the systems submitted by the University of Groningen to the English– Kazakh language pair (both translation directions) for the WMT 2019 news translation task. We explore the potential benefits of (i) morphological segmentation (both unsupervised and rule-based), given the agglutinative nature of Kazakh, (ii) data from two additional languages (Turkish and Russian), given the scarcity of English–Kazakh data and (iii) synthetic data, both for the source and for the target language. Our best submissions ranked second for Kazakh→English and third for English→Kazakh in terms of the BLEU automatic evaluation metric.</abstract>
<identifier type="citekey">toral-etal-2019-neural</identifier>
<identifier type="doi">10.18653/v1/W19-5343</identifier>
<location>
<url>https://aclanthology.org/W19-5343</url>
</location>
<part>
<date>2019-aug</date>
<extent unit="page">
<start>386</start>
<end>392</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Neural Machine Translation for English–Kazakh with Morphological Segmentation and Synthetic Data
%A Toral, Antonio
%A Edman, Lukas
%A Yeshmagambetova, Galiya
%A Spenader, Jennifer
%S Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1)
%D 2019
%8 aug
%I Association for Computational Linguistics
%C Florence, Italy
%F toral-etal-2019-neural
%X This paper presents the systems submitted by the University of Groningen to the English– Kazakh language pair (both translation directions) for the WMT 2019 news translation task. We explore the potential benefits of (i) morphological segmentation (both unsupervised and rule-based), given the agglutinative nature of Kazakh, (ii) data from two additional languages (Turkish and Russian), given the scarcity of English–Kazakh data and (iii) synthetic data, both for the source and for the target language. Our best submissions ranked second for Kazakh→English and third for English→Kazakh in terms of the BLEU automatic evaluation metric.
%R 10.18653/v1/W19-5343
%U https://aclanthology.org/W19-5343
%U https://doi.org/10.18653/v1/W19-5343
%P 386-392
Markdown (Informal)
[Neural Machine Translation for English–Kazakh with Morphological Segmentation and Synthetic Data](https://aclanthology.org/W19-5343) (Toral et al., 2019)
ACL