@inproceedings{moghe-etal-2020-university,
title = "The {U}niversity of {E}dinburgh-{U}ppsala {U}niversity{'}s Submission to the {WMT} 2020 Chat Translation Task",
author = "Moghe, Nikita and
Hardmeier, Christian and
Bawden, Rachel",
editor = {Barrault, Lo{\"\i}c and
Bojar, Ond{\v{r}}ej and
Bougares, Fethi and
Chatterjee, Rajen and
Costa-juss{\`a}, Marta R. and
Federmann, Christian and
Fishel, Mark and
Fraser, Alexander and
Graham, Yvette and
Guzman, Paco and
Haddow, Barry and
Huck, Matthias and
Yepes, Antonio Jimeno and
Koehn, Philipp and
Martins, Andr{\'e} and
Morishita, Makoto and
Monz, Christof and
Nagata, Masaaki and
Nakazawa, Toshiaki and
Negri, Matteo},
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-1.58",
pages = "473--478",
abstract = "This paper describes the joint submission of the University of Edinburgh and Uppsala University to the WMT{'}20 chat translation task for both language directions (English-German). We use existing state-of-the-art machine translation models trained on news data and fine-tune them on in-domain and pseudo-in-domain web crawled data. Our baseline systems are transformer-big models that are pre-trained on the WMT{'}19 News Translation task and fine-tuned on pseudo-in-domain web crawled data and in-domain task data. We also experiment with (i) adaptation using speaker and domain tags and (ii) using different types and amounts of preceding context. We observe that contrarily to expectations, exploiting context degrades the results (and on analysis the data is not highly contextual). However using domain tags does improve scores according to the automatic evaluation. Our final primary systems use domain tags and are ensembles of 4 models, with noisy channel reranking of outputs. Our en-de system was ranked second in the shared task while our de-en system outperformed all the other systems.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="moghe-etal-2020-university">
<titleInfo>
<title>The University of Edinburgh-Uppsala University’s Submission to the WMT 2020 Chat Translation Task</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nikita</namePart>
<namePart type="family">Moghe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christian</namePart>
<namePart type="family">Hardmeier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rachel</namePart>
<namePart type="family">Bawden</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth Conference on Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Loïc</namePart>
<namePart type="family">Barrault</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ondřej</namePart>
<namePart type="family">Bojar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fethi</namePart>
<namePart type="family">Bougares</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rajen</namePart>
<namePart type="family">Chatterjee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marta</namePart>
<namePart type="given">R</namePart>
<namePart type="family">Costa-jussà</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christian</namePart>
<namePart type="family">Federmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Fishel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Fraser</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yvette</namePart>
<namePart type="family">Graham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paco</namePart>
<namePart type="family">Guzman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barry</namePart>
<namePart type="family">Haddow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthias</namePart>
<namePart type="family">Huck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="given">Jimeno</namePart>
<namePart type="family">Yepes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philipp</namePart>
<namePart type="family">Koehn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">André</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Makoto</namePart>
<namePart type="family">Morishita</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christof</namePart>
<namePart type="family">Monz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Masaaki</namePart>
<namePart type="family">Nagata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Toshiaki</namePart>
<namePart type="family">Nakazawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matteo</namePart>
<namePart type="family">Negri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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 describes the joint submission of the University of Edinburgh and Uppsala University to the WMT’20 chat translation task for both language directions (English-German). We use existing state-of-the-art machine translation models trained on news data and fine-tune them on in-domain and pseudo-in-domain web crawled data. Our baseline systems are transformer-big models that are pre-trained on the WMT’19 News Translation task and fine-tuned on pseudo-in-domain web crawled data and in-domain task data. We also experiment with (i) adaptation using speaker and domain tags and (ii) using different types and amounts of preceding context. We observe that contrarily to expectations, exploiting context degrades the results (and on analysis the data is not highly contextual). However using domain tags does improve scores according to the automatic evaluation. Our final primary systems use domain tags and are ensembles of 4 models, with noisy channel reranking of outputs. Our en-de system was ranked second in the shared task while our de-en system outperformed all the other systems.</abstract>
<identifier type="citekey">moghe-etal-2020-university</identifier>
<location>
<url>https://aclanthology.org/2020.wmt-1.58</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>473</start>
<end>478</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The University of Edinburgh-Uppsala University’s Submission to the WMT 2020 Chat Translation Task
%A Moghe, Nikita
%A Hardmeier, Christian
%A Bawden, Rachel
%Y Barrault, Loïc
%Y Bojar, Ondřej
%Y Bougares, Fethi
%Y Chatterjee, Rajen
%Y Costa-jussà, Marta R.
%Y Federmann, Christian
%Y Fishel, Mark
%Y Fraser, Alexander
%Y Graham, Yvette
%Y Guzman, Paco
%Y Haddow, Barry
%Y Huck, Matthias
%Y Yepes, Antonio Jimeno
%Y Koehn, Philipp
%Y Martins, André
%Y Morishita, Makoto
%Y Monz, Christof
%Y Nagata, Masaaki
%Y Nakazawa, Toshiaki
%Y Negri, Matteo
%S Proceedings of the Fifth Conference on Machine Translation
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F moghe-etal-2020-university
%X This paper describes the joint submission of the University of Edinburgh and Uppsala University to the WMT’20 chat translation task for both language directions (English-German). We use existing state-of-the-art machine translation models trained on news data and fine-tune them on in-domain and pseudo-in-domain web crawled data. Our baseline systems are transformer-big models that are pre-trained on the WMT’19 News Translation task and fine-tuned on pseudo-in-domain web crawled data and in-domain task data. We also experiment with (i) adaptation using speaker and domain tags and (ii) using different types and amounts of preceding context. We observe that contrarily to expectations, exploiting context degrades the results (and on analysis the data is not highly contextual). However using domain tags does improve scores according to the automatic evaluation. Our final primary systems use domain tags and are ensembles of 4 models, with noisy channel reranking of outputs. Our en-de system was ranked second in the shared task while our de-en system outperformed all the other systems.
%U https://aclanthology.org/2020.wmt-1.58
%P 473-478
Markdown (Informal)
[The University of Edinburgh-Uppsala University’s Submission to the WMT 2020 Chat Translation Task](https://aclanthology.org/2020.wmt-1.58) (Moghe et al., WMT 2020)
ACL