@inproceedings{zhang-etal-2021-multi,
title = "Multi-Hop Transformer for Document-Level Machine Translation",
author = "Zhang, Long and
Zhang, Tong and
Zhang, Haibo and
Yang, Baosong and
Ye, Wei and
Zhang, Shikun",
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.309",
doi = "10.18653/v1/2021.naacl-main.309",
pages = "3953--3963",
abstract = "Document-level neural machine translation (NMT) has proven to be of profound value for its effectiveness on capturing contextual information. Nevertheless, existing approaches 1) simply introduce the representations of context sentences without explicitly characterizing the inter-sentence reasoning process; and 2) feed ground-truth target contexts as extra inputs at the training time, thus facing the problem of exposure bias. We approach these problems with an inspiration from human behavior {--} human translators ordinarily emerge a translation draft in their mind and progressively revise it according to the reasoning in discourse. To this end, we propose a novel Multi-Hop Transformer (MHT) which offers NMT abilities to explicitly model the human-like draft-editing and reasoning process. Specifically, our model serves the sentence-level translation as a draft and properly refines its representations by attending to multiple antecedent sentences iteratively. Experiments on four widely used document translation tasks demonstrate that our method can significantly improve document-level translation performance and can tackle discourse phenomena, such as coreference error and the problem of polysemy.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2021-multi">
<titleInfo>
<title>Multi-Hop Transformer for Document-Level Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Long</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haibo</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Baosong</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Ye</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shikun</namePart>
<namePart type="family">Zhang</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-level neural machine translation (NMT) has proven to be of profound value for its effectiveness on capturing contextual information. Nevertheless, existing approaches 1) simply introduce the representations of context sentences without explicitly characterizing the inter-sentence reasoning process; and 2) feed ground-truth target contexts as extra inputs at the training time, thus facing the problem of exposure bias. We approach these problems with an inspiration from human behavior – human translators ordinarily emerge a translation draft in their mind and progressively revise it according to the reasoning in discourse. To this end, we propose a novel Multi-Hop Transformer (MHT) which offers NMT abilities to explicitly model the human-like draft-editing and reasoning process. Specifically, our model serves the sentence-level translation as a draft and properly refines its representations by attending to multiple antecedent sentences iteratively. Experiments on four widely used document translation tasks demonstrate that our method can significantly improve document-level translation performance and can tackle discourse phenomena, such as coreference error and the problem of polysemy.</abstract>
<identifier type="citekey">zhang-etal-2021-multi</identifier>
<identifier type="doi">10.18653/v1/2021.naacl-main.309</identifier>
<location>
<url>https://aclanthology.org/2021.naacl-main.309</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>3953</start>
<end>3963</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multi-Hop Transformer for Document-Level Machine Translation
%A Zhang, Long
%A Zhang, Tong
%A Zhang, Haibo
%A Yang, Baosong
%A Ye, Wei
%A Zhang, Shikun
%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 zhang-etal-2021-multi
%X Document-level neural machine translation (NMT) has proven to be of profound value for its effectiveness on capturing contextual information. Nevertheless, existing approaches 1) simply introduce the representations of context sentences without explicitly characterizing the inter-sentence reasoning process; and 2) feed ground-truth target contexts as extra inputs at the training time, thus facing the problem of exposure bias. We approach these problems with an inspiration from human behavior – human translators ordinarily emerge a translation draft in their mind and progressively revise it according to the reasoning in discourse. To this end, we propose a novel Multi-Hop Transformer (MHT) which offers NMT abilities to explicitly model the human-like draft-editing and reasoning process. Specifically, our model serves the sentence-level translation as a draft and properly refines its representations by attending to multiple antecedent sentences iteratively. Experiments on four widely used document translation tasks demonstrate that our method can significantly improve document-level translation performance and can tackle discourse phenomena, such as coreference error and the problem of polysemy.
%R 10.18653/v1/2021.naacl-main.309
%U https://aclanthology.org/2021.naacl-main.309
%U https://doi.org/10.18653/v1/2021.naacl-main.309
%P 3953-3963
Markdown (Informal)
[Multi-Hop Transformer for Document-Level Machine Translation](https://aclanthology.org/2021.naacl-main.309) (Zhang et al., NAACL 2021)
ACL
- Long Zhang, Tong Zhang, Haibo Zhang, Baosong Yang, Wei Ye, and Shikun Zhang. 2021. Multi-Hop Transformer for Document-Level Machine Translation. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 3953–3963, Online. Association for Computational Linguistics.