@inproceedings{guo-nguyen-2020-document,
title = "Document-Level Neural Machine Translation Using {BERT} as Context Encoder",
author = "Guo, Zhiyu and
Nguyen, Minh Le",
editor = "Shmueli, Boaz and
Huang, Yin Jou",
booktitle = "Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing: Student Research Workshop",
month = dec,
year = "2020",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.aacl-srw.15",
pages = "101--107",
abstract = "Large-scale pre-trained representations such as BERT have been widely used in many natural language understanding tasks. The methods of incorporating BERT into document-level machine translation are still being explored. BERT is able to understand sentence relationships since BERT is pre-trained using the next sentence prediction task. In our work, we leverage this property to improve document-level machine translation. In our proposed model, BERT performs as a context encoder to achieve document-level contextual information, which is then integrated into both the encoder and decoder. Experiment results show that our proposed method can significantly outperform strong document-level machine translation baselines on BLEU score. Moreover, the ablation study shows our method can capture document-level context information to boost translation performance.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="guo-nguyen-2020-document">
<titleInfo>
<title>Document-Level Neural Machine Translation Using BERT as Context Encoder</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhiyu</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minh</namePart>
<namePart type="given">Le</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing: Student Research Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Boaz</namePart>
<namePart type="family">Shmueli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yin</namePart>
<namePart type="given">Jou</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Large-scale pre-trained representations such as BERT have been widely used in many natural language understanding tasks. The methods of incorporating BERT into document-level machine translation are still being explored. BERT is able to understand sentence relationships since BERT is pre-trained using the next sentence prediction task. In our work, we leverage this property to improve document-level machine translation. In our proposed model, BERT performs as a context encoder to achieve document-level contextual information, which is then integrated into both the encoder and decoder. Experiment results show that our proposed method can significantly outperform strong document-level machine translation baselines on BLEU score. Moreover, the ablation study shows our method can capture document-level context information to boost translation performance.</abstract>
<identifier type="citekey">guo-nguyen-2020-document</identifier>
<location>
<url>https://aclanthology.org/2020.aacl-srw.15</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>101</start>
<end>107</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Document-Level Neural Machine Translation Using BERT as Context Encoder
%A Guo, Zhiyu
%A Nguyen, Minh Le
%Y Shmueli, Boaz
%Y Huang, Yin Jou
%S Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing: Student Research Workshop
%D 2020
%8 December
%I Association for Computational Linguistics
%C Suzhou, China
%F guo-nguyen-2020-document
%X Large-scale pre-trained representations such as BERT have been widely used in many natural language understanding tasks. The methods of incorporating BERT into document-level machine translation are still being explored. BERT is able to understand sentence relationships since BERT is pre-trained using the next sentence prediction task. In our work, we leverage this property to improve document-level machine translation. In our proposed model, BERT performs as a context encoder to achieve document-level contextual information, which is then integrated into both the encoder and decoder. Experiment results show that our proposed method can significantly outperform strong document-level machine translation baselines on BLEU score. Moreover, the ablation study shows our method can capture document-level context information to boost translation performance.
%U https://aclanthology.org/2020.aacl-srw.15
%P 101-107
Markdown (Informal)
[Document-Level Neural Machine Translation Using BERT as Context Encoder](https://aclanthology.org/2020.aacl-srw.15) (Guo & Nguyen, AACL 2020)
ACL
- Zhiyu Guo and Minh Le Nguyen. 2020. Document-Level Neural Machine Translation Using BERT as Context Encoder. In Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing: Student Research Workshop, pages 101–107, Suzhou, China. Association for Computational Linguistics.