@inproceedings{marie-etal-2020-combination,
title = "Combination of Neural Machine Translation Systems at {WMT}20",
author = "Marie, Benjamin and
Rubino, Raphael and
Fujita, Atsushi",
booktitle = "Proceedings of the Fifth Conference on Machine Translation",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.wmt-1.23",
pages = "230--238",
abstract = "This paper presents neural machine translation systems and their combination built for the WMT20 English-Polish and Japanese-{\textgreater}English translation tasks. We show that using a Transformer Big architecture, additional training data synthesized from monolingual data, and combining many NMT systems through n-best list reranking improve translation quality. However, while we observed such improvements on the validation data, we did not observed similar improvements on the test data. Our analysis reveals that the presence of translationese texts in the validation data led us to take decisions in building NMT systems that were not optimal to obtain the best results on the test data.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="marie-etal-2020-combination">
<titleInfo>
<title>Combination of Neural Machine Translation Systems at WMT20</title>
</titleInfo>
<name type="personal">
<namePart type="given">Benjamin</namePart>
<namePart type="family">Marie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raphael</namePart>
<namePart type="family">Rubino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Atsushi</namePart>
<namePart type="family">Fujita</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-nov</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth Conference on Machine Translation</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents neural machine translation systems and their combination built for the WMT20 English-Polish and Japanese-\textgreaterEnglish translation tasks. We show that using a Transformer Big architecture, additional training data synthesized from monolingual data, and combining many NMT systems through n-best list reranking improve translation quality. However, while we observed such improvements on the validation data, we did not observed similar improvements on the test data. Our analysis reveals that the presence of translationese texts in the validation data led us to take decisions in building NMT systems that were not optimal to obtain the best results on the test data.</abstract>
<identifier type="citekey">marie-etal-2020-combination</identifier>
<location>
<url>https://aclanthology.org/2020.wmt-1.23</url>
</location>
<part>
<date>2020-nov</date>
<extent unit="page">
<start>230</start>
<end>238</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Combination of Neural Machine Translation Systems at WMT20
%A Marie, Benjamin
%A Rubino, Raphael
%A Fujita, Atsushi
%S Proceedings of the Fifth Conference on Machine Translation
%D 2020
%8 nov
%I Association for Computational Linguistics
%C Online
%F marie-etal-2020-combination
%X This paper presents neural machine translation systems and their combination built for the WMT20 English-Polish and Japanese-\textgreaterEnglish translation tasks. We show that using a Transformer Big architecture, additional training data synthesized from monolingual data, and combining many NMT systems through n-best list reranking improve translation quality. However, while we observed such improvements on the validation data, we did not observed similar improvements on the test data. Our analysis reveals that the presence of translationese texts in the validation data led us to take decisions in building NMT systems that were not optimal to obtain the best results on the test data.
%U https://aclanthology.org/2020.wmt-1.23
%P 230-238
Markdown (Informal)
[Combination of Neural Machine Translation Systems at WMT20](https://aclanthology.org/2020.wmt-1.23) (Marie et al., WMT 2020)
ACL