@inproceedings{liu-zhang-2020-corpora,
title = "Corpora for Document-Level Neural Machine Translation",
author = "Liu, Siyou and
Zhang, Xiaojun",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.466",
pages = "3775--3781",
abstract = "Instead of translating sentences in isolation, document-level machine translation aims to capture discourse dependencies across sentences by considering a document as a whole. In recent years, there have been more interests in modelling larger context for the state-of-the-art neural machine translation (NMT). Although various document-level NMT models have shown significant improvements, there nonetheless exist three main problems: 1) compared with sentence-level translation tasks, the data for training robust document-level models are relatively low-resourced; 2) experiments in previous work are conducted on their own datasets which vary in size, domain and language; 3) proposed approaches are implemented on distinct NMT architectures such as recurrent neural networks (RNNs) and self-attention networks (SANs). In this paper, we aims to alleviate the low-resource and under-universality problems for document-level NMT. First, we collect a large number of existing document-level corpora, which covers 7 language pairs and 6 domains. In order to address resource sparsity, we construct a novel document parallel corpus in Chinese-Portuguese, which is a non-English-centred and low-resourced language pair. Besides, we implement and evaluate the commonly-cited document-level method on top of the advanced Transformer model with universal settings. Finally, we not only demonstrate the effectiveness and universality of document-level NMT, but also release the preprocessed data, source code and trained models for comparison and reproducibility.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-zhang-2020-corpora">
<titleInfo>
<title>Corpora for Document-Level Neural Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Siyou</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaojun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>Instead of translating sentences in isolation, document-level machine translation aims to capture discourse dependencies across sentences by considering a document as a whole. In recent years, there have been more interests in modelling larger context for the state-of-the-art neural machine translation (NMT). Although various document-level NMT models have shown significant improvements, there nonetheless exist three main problems: 1) compared with sentence-level translation tasks, the data for training robust document-level models are relatively low-resourced; 2) experiments in previous work are conducted on their own datasets which vary in size, domain and language; 3) proposed approaches are implemented on distinct NMT architectures such as recurrent neural networks (RNNs) and self-attention networks (SANs). In this paper, we aims to alleviate the low-resource and under-universality problems for document-level NMT. First, we collect a large number of existing document-level corpora, which covers 7 language pairs and 6 domains. In order to address resource sparsity, we construct a novel document parallel corpus in Chinese-Portuguese, which is a non-English-centred and low-resourced language pair. Besides, we implement and evaluate the commonly-cited document-level method on top of the advanced Transformer model with universal settings. Finally, we not only demonstrate the effectiveness and universality of document-level NMT, but also release the preprocessed data, source code and trained models for comparison and reproducibility.</abstract>
<identifier type="citekey">liu-zhang-2020-corpora</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.466</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>3775</start>
<end>3781</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Corpora for Document-Level Neural Machine Translation
%A Liu, Siyou
%A Zhang, Xiaojun
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F liu-zhang-2020-corpora
%X Instead of translating sentences in isolation, document-level machine translation aims to capture discourse dependencies across sentences by considering a document as a whole. In recent years, there have been more interests in modelling larger context for the state-of-the-art neural machine translation (NMT). Although various document-level NMT models have shown significant improvements, there nonetheless exist three main problems: 1) compared with sentence-level translation tasks, the data for training robust document-level models are relatively low-resourced; 2) experiments in previous work are conducted on their own datasets which vary in size, domain and language; 3) proposed approaches are implemented on distinct NMT architectures such as recurrent neural networks (RNNs) and self-attention networks (SANs). In this paper, we aims to alleviate the low-resource and under-universality problems for document-level NMT. First, we collect a large number of existing document-level corpora, which covers 7 language pairs and 6 domains. In order to address resource sparsity, we construct a novel document parallel corpus in Chinese-Portuguese, which is a non-English-centred and low-resourced language pair. Besides, we implement and evaluate the commonly-cited document-level method on top of the advanced Transformer model with universal settings. Finally, we not only demonstrate the effectiveness and universality of document-level NMT, but also release the preprocessed data, source code and trained models for comparison and reproducibility.
%U https://aclanthology.org/2020.lrec-1.466
%P 3775-3781
Markdown (Informal)
[Corpora for Document-Level Neural Machine Translation](https://aclanthology.org/2020.lrec-1.466) (Liu & Zhang, LREC 2020)
ACL