@inproceedings{scherrer-etal-2019-university,
title = "The {U}niversity of {H}elsinki Submissions to the {WMT}19 Similar Language Translation Task",
author = "Scherrer, Yves and
V{\'a}zquez, Ra{\'u}l and
Virpioja, Sami",
booktitle = "Proceedings of the Fourth Conference on Machine Translation (Volume 3: Shared Task Papers, Day 2)",
month = aug,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-5432",
doi = "10.18653/v1/W19-5432",
pages = "236--244",
abstract = "This paper describes the University of Helsinki Language Technology group{'}s participation in the WMT 2019 similar language translation task. We trained neural machine translation models for the language pairs Czech {\textless}-{\textgreater} Polish and Spanish {\textless}-{\textgreater} Portuguese. Our experiments focused on different subword segmentation methods, and in particular on the comparison of a cognate-aware segmentation method, Cognate Morfessor, with character segmentation and unsupervised segmentation methods for which the data from different languages were simply concatenated. We did not observe major benefits from cognate-aware segmentation methods, but further research may be needed to explore larger parts of the parameter space. Character-level models proved to be competitive for translation between Spanish and Portuguese, but they are slower in training and decoding.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="scherrer-etal-2019-university">
<titleInfo>
<title>The University of Helsinki Submissions to the WMT19 Similar Language Translation Task</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yves</namePart>
<namePart type="family">Scherrer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raúl</namePart>
<namePart type="family">Vázquez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sami</namePart>
<namePart type="family">Virpioja</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 3: Shared Task Papers, Day 2)</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 describes the University of Helsinki Language Technology group’s participation in the WMT 2019 similar language translation task. We trained neural machine translation models for the language pairs Czech \textless-\textgreater Polish and Spanish \textless-\textgreater Portuguese. Our experiments focused on different subword segmentation methods, and in particular on the comparison of a cognate-aware segmentation method, Cognate Morfessor, with character segmentation and unsupervised segmentation methods for which the data from different languages were simply concatenated. We did not observe major benefits from cognate-aware segmentation methods, but further research may be needed to explore larger parts of the parameter space. Character-level models proved to be competitive for translation between Spanish and Portuguese, but they are slower in training and decoding.</abstract>
<identifier type="citekey">scherrer-etal-2019-university</identifier>
<identifier type="doi">10.18653/v1/W19-5432</identifier>
<location>
<url>https://aclanthology.org/W19-5432</url>
</location>
<part>
<date>2019-aug</date>
<extent unit="page">
<start>236</start>
<end>244</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The University of Helsinki Submissions to the WMT19 Similar Language Translation Task
%A Scherrer, Yves
%A Vázquez, Raúl
%A Virpioja, Sami
%S Proceedings of the Fourth Conference on Machine Translation (Volume 3: Shared Task Papers, Day 2)
%D 2019
%8 aug
%I Association for Computational Linguistics
%C Florence, Italy
%F scherrer-etal-2019-university
%X This paper describes the University of Helsinki Language Technology group’s participation in the WMT 2019 similar language translation task. We trained neural machine translation models for the language pairs Czech \textless-\textgreater Polish and Spanish \textless-\textgreater Portuguese. Our experiments focused on different subword segmentation methods, and in particular on the comparison of a cognate-aware segmentation method, Cognate Morfessor, with character segmentation and unsupervised segmentation methods for which the data from different languages were simply concatenated. We did not observe major benefits from cognate-aware segmentation methods, but further research may be needed to explore larger parts of the parameter space. Character-level models proved to be competitive for translation between Spanish and Portuguese, but they are slower in training and decoding.
%R 10.18653/v1/W19-5432
%U https://aclanthology.org/W19-5432
%U https://doi.org/10.18653/v1/W19-5432
%P 236-244
Markdown (Informal)
[The University of Helsinki Submissions to the WMT19 Similar Language Translation Task](https://aclanthology.org/W19-5432) (Scherrer et al., 2019)
ACL