@inproceedings{chen-etal-2021-breaking,
title = "[RETRACTED] Breaking the Corpus Bottleneck for Context-Aware Neural Machine Translation with Cross-Task Pre-training",
author = "Chen, Linqing and
Li, Junhui and
Gong, Zhengxian and
Chen, Boxing and
Luo, Weihua and
Zhang, Min and
Zhou, Guodong",
editor = "Zong, Chengqing and
Xia, Fei and
Li, Wenjie and
Navigli, Roberto",
booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.acl-long.222",
doi = "10.18653/v1/2021.acl-long.222",
pages = "2851--2861",
abstract = "Context-aware neural machine translation (NMT) remains challenging due to the lack of large-scale document-level parallel corpora. To break the corpus bottleneck, in this paper we aim to improve context-aware NMT by taking the advantage of the availability of both large-scale sentence-level parallel dataset and source-side monolingual documents. To this end, we propose two pre-training tasks. One learns to translate a sentence from source language to target language on the sentence-level parallel dataset while the other learns to translate a document from deliberately noised to original on the monolingual documents. Importantly, the two pre-training tasks are jointly and simultaneously learned via the same model, thereafter fine-tuned on scale-limited parallel documents from both sentence-level and document-level perspectives. Experimental results on four translation tasks show that our approach significantly improves translation performance. One nice property of our approach is that the fine-tuned model can be used to translate both sentences and documents.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2021-breaking">
<titleInfo>
<title>[RETRACTED] Breaking the Corpus Bottleneck for Context-Aware Neural Machine Translation with Cross-Task Pre-training</title>
</titleInfo>
<name type="personal">
<namePart type="given">Linqing</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junhui</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhengxian</namePart>
<namePart type="family">Gong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Boxing</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weihua</namePart>
<namePart type="family">Luo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guodong</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Xia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenjie</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roberto</namePart>
<namePart type="family">Navigli</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>Context-aware neural machine translation (NMT) remains challenging due to the lack of large-scale document-level parallel corpora. To break the corpus bottleneck, in this paper we aim to improve context-aware NMT by taking the advantage of the availability of both large-scale sentence-level parallel dataset and source-side monolingual documents. To this end, we propose two pre-training tasks. One learns to translate a sentence from source language to target language on the sentence-level parallel dataset while the other learns to translate a document from deliberately noised to original on the monolingual documents. Importantly, the two pre-training tasks are jointly and simultaneously learned via the same model, thereafter fine-tuned on scale-limited parallel documents from both sentence-level and document-level perspectives. Experimental results on four translation tasks show that our approach significantly improves translation performance. One nice property of our approach is that the fine-tuned model can be used to translate both sentences and documents.</abstract>
<identifier type="citekey">chen-etal-2021-breaking</identifier>
<identifier type="doi">10.18653/v1/2021.acl-long.222</identifier>
<location>
<url>https://aclanthology.org/2021.acl-long.222</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>2851</start>
<end>2861</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T [RETRACTED] Breaking the Corpus Bottleneck for Context-Aware Neural Machine Translation with Cross-Task Pre-training
%A Chen, Linqing
%A Li, Junhui
%A Gong, Zhengxian
%A Chen, Boxing
%A Luo, Weihua
%A Zhang, Min
%A Zhou, Guodong
%Y Zong, Chengqing
%Y Xia, Fei
%Y Li, Wenjie
%Y Navigli, Roberto
%S Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F chen-etal-2021-breaking
%X Context-aware neural machine translation (NMT) remains challenging due to the lack of large-scale document-level parallel corpora. To break the corpus bottleneck, in this paper we aim to improve context-aware NMT by taking the advantage of the availability of both large-scale sentence-level parallel dataset and source-side monolingual documents. To this end, we propose two pre-training tasks. One learns to translate a sentence from source language to target language on the sentence-level parallel dataset while the other learns to translate a document from deliberately noised to original on the monolingual documents. Importantly, the two pre-training tasks are jointly and simultaneously learned via the same model, thereafter fine-tuned on scale-limited parallel documents from both sentence-level and document-level perspectives. Experimental results on four translation tasks show that our approach significantly improves translation performance. One nice property of our approach is that the fine-tuned model can be used to translate both sentences and documents.
%R 10.18653/v1/2021.acl-long.222
%U https://aclanthology.org/2021.acl-long.222
%U https://doi.org/10.18653/v1/2021.acl-long.222
%P 2851-2861
Markdown (Informal)
[Breaking the Corpus Bottleneck for Context-Aware Neural Machine Translation with Cross-Task Pre-training](https://aclanthology.org/2021.acl-long.222) (Chen et al., ACL-IJCNLP 2021)
ACL