@inproceedings{yang-etal-2021-context,
title = "Context-Interactive Pre-Training for Document Machine Translation",
author = "Yang, Pengcheng and
Zhang, Pei and
Chen, Boxing and
Xie, Jun and
Luo, Weihua",
editor = "Toutanova, Kristina and
Rumshisky, Anna and
Zettlemoyer, Luke and
Hakkani-Tur, Dilek and
Beltagy, Iz and
Bethard, Steven and
Cotterell, Ryan and
Chakraborty, Tanmoy and
Zhou, Yichao",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.naacl-main.281/",
doi = "10.18653/v1/2021.naacl-main.281",
pages = "3589--3595",
abstract = "Document machine translation aims to translate the source sentence into the target language in the presence of additional contextual information. However, it typically suffers from a lack of doc-level bilingual data. To remedy this, here we propose a simple yet effective context-interactive pre-training approach, which targets benefiting from external large-scale corpora. The proposed model performs inter sentence generation to capture the cross-sentence dependency within the target document, and cross sentence translation to make better use of valuable contextual information. Comprehensive experiments illustrate that our approach can achieve state-of-the-art performance on three benchmark datasets, which significantly outperforms a variety of baselines."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-etal-2021-context">
<titleInfo>
<title>Context-Interactive Pre-Training for Document Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pengcheng</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pei</namePart>
<namePart type="family">Zhang</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">Jun</namePart>
<namePart type="family">Xie</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>
<originInfo>
<dateIssued>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kristina</namePart>
<namePart type="family">Toutanova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rumshisky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luke</namePart>
<namePart type="family">Zettlemoyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dilek</namePart>
<namePart type="family">Hakkani-Tur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iz</namePart>
<namePart type="family">Beltagy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Cotterell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yichao</namePart>
<namePart type="family">Zhou</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>Document machine translation aims to translate the source sentence into the target language in the presence of additional contextual information. However, it typically suffers from a lack of doc-level bilingual data. To remedy this, here we propose a simple yet effective context-interactive pre-training approach, which targets benefiting from external large-scale corpora. The proposed model performs inter sentence generation to capture the cross-sentence dependency within the target document, and cross sentence translation to make better use of valuable contextual information. Comprehensive experiments illustrate that our approach can achieve state-of-the-art performance on three benchmark datasets, which significantly outperforms a variety of baselines.</abstract>
<identifier type="citekey">yang-etal-2021-context</identifier>
<identifier type="doi">10.18653/v1/2021.naacl-main.281</identifier>
<location>
<url>https://aclanthology.org/2021.naacl-main.281/</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>3589</start>
<end>3595</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Context-Interactive Pre-Training for Document Machine Translation
%A Yang, Pengcheng
%A Zhang, Pei
%A Chen, Boxing
%A Xie, Jun
%A Luo, Weihua
%Y Toutanova, Kristina
%Y Rumshisky, Anna
%Y Zettlemoyer, Luke
%Y Hakkani-Tur, Dilek
%Y Beltagy, Iz
%Y Bethard, Steven
%Y Cotterell, Ryan
%Y Chakraborty, Tanmoy
%Y Zhou, Yichao
%S Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2021
%8 June
%I Association for Computational Linguistics
%C Online
%F yang-etal-2021-context
%X Document machine translation aims to translate the source sentence into the target language in the presence of additional contextual information. However, it typically suffers from a lack of doc-level bilingual data. To remedy this, here we propose a simple yet effective context-interactive pre-training approach, which targets benefiting from external large-scale corpora. The proposed model performs inter sentence generation to capture the cross-sentence dependency within the target document, and cross sentence translation to make better use of valuable contextual information. Comprehensive experiments illustrate that our approach can achieve state-of-the-art performance on three benchmark datasets, which significantly outperforms a variety of baselines.
%R 10.18653/v1/2021.naacl-main.281
%U https://aclanthology.org/2021.naacl-main.281/
%U https://doi.org/10.18653/v1/2021.naacl-main.281
%P 3589-3595
Markdown (Informal)
[Context-Interactive Pre-Training for Document Machine Translation](https://aclanthology.org/2021.naacl-main.281/) (Yang et al., NAACL 2021)
ACL
- Pengcheng Yang, Pei Zhang, Boxing Chen, Jun Xie, and Weihua Luo. 2021. Context-Interactive Pre-Training for Document Machine Translation. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 3589–3595, Online. Association for Computational Linguistics.