@inproceedings{junczys-dowmunt-2019-microsoft,
title = "{M}icrosoft Translator at {WMT} 2019: Towards Large-Scale Document-Level Neural Machine Translation",
author = "Junczys-Dowmunt, Marcin",
editor = "Bojar, Ond{\v{r}}ej and
Chatterjee, Rajen and
Federmann, Christian and
Fishel, Mark and
Graham, Yvette and
Haddow, Barry and
Huck, Matthias and
Yepes, Antonio Jimeno and
Koehn, Philipp and
Martins, Andr{\'e} and
Monz, Christof and
Negri, Matteo and
N{\'e}v{\'e}ol, Aur{\'e}lie and
Neves, Mariana and
Post, Matt and
Turchi, Marco and
Verspoor, Karin",
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/W19-5321",
doi = "10.18653/v1/W19-5321",
pages = "225--233",
abstract = "This paper describes the Microsoft Translator submissions to the WMT19 news translation shared task for English-German. Our main focus is document-level neural machine translation with deep transformer models. We start with strong sentence-level baselines, trained on large-scale data created via data-filtering and noisy back-translation and find that back-translation seems to mainly help with translationese input. We explore fine-tuning techniques, deeper models and different ensembling strategies to counter these effects. Using document boundaries present in the authentic and synthetic parallel data, we create sequences of up to 1000 subword segments and train transformer translation models. We experiment with data augmentation techniques for the smaller authentic data with document-boundaries and for larger authentic data without boundaries. We further explore multi-task training for the incorporation of document-level source language monolingual data via the BERT-objective on the encoder and two-pass decoding for combinations of sentence-level and document-level systems. Based on preliminary human evaluation results, evaluators strongly prefer the document-level systems over our comparable sentence-level system. The document-level systems also seem to score higher than the human references in source-based direct assessment.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="junczys-dowmunt-2019-microsoft">
<titleInfo>
<title>Microsoft Translator at WMT 2019: Towards Large-Scale Document-Level Neural Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marcin</namePart>
<namePart type="family">Junczys-Dowmunt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-08</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>
<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">Rajen</namePart>
<namePart type="family">Chatterjee</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">Yvette</namePart>
<namePart type="family">Graham</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">Christof</namePart>
<namePart type="family">Monz</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>
<name type="personal">
<namePart type="given">Aurélie</namePart>
<namePart type="family">Névéol</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mariana</namePart>
<namePart type="family">Neves</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matt</namePart>
<namePart type="family">Post</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Turchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karin</namePart>
<namePart type="family">Verspoor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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 Microsoft Translator submissions to the WMT19 news translation shared task for English-German. Our main focus is document-level neural machine translation with deep transformer models. We start with strong sentence-level baselines, trained on large-scale data created via data-filtering and noisy back-translation and find that back-translation seems to mainly help with translationese input. We explore fine-tuning techniques, deeper models and different ensembling strategies to counter these effects. Using document boundaries present in the authentic and synthetic parallel data, we create sequences of up to 1000 subword segments and train transformer translation models. We experiment with data augmentation techniques for the smaller authentic data with document-boundaries and for larger authentic data without boundaries. We further explore multi-task training for the incorporation of document-level source language monolingual data via the BERT-objective on the encoder and two-pass decoding for combinations of sentence-level and document-level systems. Based on preliminary human evaluation results, evaluators strongly prefer the document-level systems over our comparable sentence-level system. The document-level systems also seem to score higher than the human references in source-based direct assessment.</abstract>
<identifier type="citekey">junczys-dowmunt-2019-microsoft</identifier>
<identifier type="doi">10.18653/v1/W19-5321</identifier>
<location>
<url>https://aclanthology.org/W19-5321</url>
</location>
<part>
<date>2019-08</date>
<extent unit="page">
<start>225</start>
<end>233</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Microsoft Translator at WMT 2019: Towards Large-Scale Document-Level Neural Machine Translation
%A Junczys-Dowmunt, Marcin
%Y Bojar, Ondřej
%Y Chatterjee, Rajen
%Y Federmann, Christian
%Y Fishel, Mark
%Y Graham, Yvette
%Y Haddow, Barry
%Y Huck, Matthias
%Y Yepes, Antonio Jimeno
%Y Koehn, Philipp
%Y Martins, André
%Y Monz, Christof
%Y Negri, Matteo
%Y Névéol, Aurélie
%Y Neves, Mariana
%Y Post, Matt
%Y Turchi, Marco
%Y Verspoor, Karin
%S Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1)
%D 2019
%8 August
%I Association for Computational Linguistics
%C Florence, Italy
%F junczys-dowmunt-2019-microsoft
%X This paper describes the Microsoft Translator submissions to the WMT19 news translation shared task for English-German. Our main focus is document-level neural machine translation with deep transformer models. We start with strong sentence-level baselines, trained on large-scale data created via data-filtering and noisy back-translation and find that back-translation seems to mainly help with translationese input. We explore fine-tuning techniques, deeper models and different ensembling strategies to counter these effects. Using document boundaries present in the authentic and synthetic parallel data, we create sequences of up to 1000 subword segments and train transformer translation models. We experiment with data augmentation techniques for the smaller authentic data with document-boundaries and for larger authentic data without boundaries. We further explore multi-task training for the incorporation of document-level source language monolingual data via the BERT-objective on the encoder and two-pass decoding for combinations of sentence-level and document-level systems. Based on preliminary human evaluation results, evaluators strongly prefer the document-level systems over our comparable sentence-level system. The document-level systems also seem to score higher than the human references in source-based direct assessment.
%R 10.18653/v1/W19-5321
%U https://aclanthology.org/W19-5321
%U https://doi.org/10.18653/v1/W19-5321
%P 225-233
Markdown (Informal)
[Microsoft Translator at WMT 2019: Towards Large-Scale Document-Level Neural Machine Translation](https://aclanthology.org/W19-5321) (Junczys-Dowmunt, WMT 2019)
ACL