@inproceedings{pham-etal-2018-karlsruhe,
title = "The Karlsruhe Institute of Technology Systems for the News Translation Task in {WMT} 2018",
author = "Pham, Ngoc-Quan and
Niehues, Jan and
Waibel, Alexander",
booktitle = "Proceedings of the Third Conference on Machine Translation: Shared Task Papers",
month = oct,
year = "2018",
address = "Belgium, Brussels",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W18-6422",
doi = "10.18653/v1/W18-6422",
pages = "467--472",
abstract = "We present our experiments in the scope of the news translation task in WMT 2018, in directions: English→German. The core of our systems is the encoder-decoder based neural machine translation models using the transformer architecture. We enhanced the model with a deeper architecture. By using techniques to limit the memory consumption, we were able to train models that are 4 times larger on one GPU and improve the performance by 1.2 BLEU points. Furthermore, we performed sentence selection for the newly available ParaCrawl corpus. Thereby, we could improve the effectiveness of the corpus by 0.5 BLEU points.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pham-etal-2018-karlsruhe">
<titleInfo>
<title>The Karlsruhe Institute of Technology Systems for the News Translation Task in WMT 2018</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ngoc-Quan</namePart>
<namePart type="family">Pham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Niehues</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Waibel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-oct</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Conference on Machine Translation: Shared Task Papers</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Belgium, Brussels</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present our experiments in the scope of the news translation task in WMT 2018, in directions: English→German. The core of our systems is the encoder-decoder based neural machine translation models using the transformer architecture. We enhanced the model with a deeper architecture. By using techniques to limit the memory consumption, we were able to train models that are 4 times larger on one GPU and improve the performance by 1.2 BLEU points. Furthermore, we performed sentence selection for the newly available ParaCrawl corpus. Thereby, we could improve the effectiveness of the corpus by 0.5 BLEU points.</abstract>
<identifier type="citekey">pham-etal-2018-karlsruhe</identifier>
<identifier type="doi">10.18653/v1/W18-6422</identifier>
<location>
<url>https://aclanthology.org/W18-6422</url>
</location>
<part>
<date>2018-oct</date>
<extent unit="page">
<start>467</start>
<end>472</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Karlsruhe Institute of Technology Systems for the News Translation Task in WMT 2018
%A Pham, Ngoc-Quan
%A Niehues, Jan
%A Waibel, Alexander
%S Proceedings of the Third Conference on Machine Translation: Shared Task Papers
%D 2018
%8 oct
%I Association for Computational Linguistics
%C Belgium, Brussels
%F pham-etal-2018-karlsruhe
%X We present our experiments in the scope of the news translation task in WMT 2018, in directions: English→German. The core of our systems is the encoder-decoder based neural machine translation models using the transformer architecture. We enhanced the model with a deeper architecture. By using techniques to limit the memory consumption, we were able to train models that are 4 times larger on one GPU and improve the performance by 1.2 BLEU points. Furthermore, we performed sentence selection for the newly available ParaCrawl corpus. Thereby, we could improve the effectiveness of the corpus by 0.5 BLEU points.
%R 10.18653/v1/W18-6422
%U https://aclanthology.org/W18-6422
%U https://doi.org/10.18653/v1/W18-6422
%P 467-472
Markdown (Informal)
[The Karlsruhe Institute of Technology Systems for the News Translation Task in WMT 2018](https://aclanthology.org/W18-6422) (Pham et al., 2018)
ACL