@inproceedings{xu-etal-2021-document-graph,
title = "Document Graph for Neural Machine Translation",
author = "Xu, Mingzhou and
Li, Liangyou and
Wong, Derek F. and
Liu, Qun and
Chao, Lidia S.",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2021",
address = "Online and Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.emnlp-main.663",
doi = "10.18653/v1/2021.emnlp-main.663",
pages = "8435--8448",
abstract = "Previous works have shown that contextual information can improve the performance of neural machine translation (NMT). However, most existing document-level NMT methods failed to leverage contexts beyond a few set of previous sentences. How to make use of the whole document as global contexts is still a challenge. To address this issue, we hypothesize that a document can be represented as a graph that connects relevant contexts regardless of their distances. We employ several types of relations, including adjacency, syntactic dependency, lexical consistency, and coreference, to construct the document graph. Then, we incorporate both source and target graphs into the conventional Transformer architecture with graph convolutional networks. Experiments on various NMT benchmarks, including IWSLT English{--}French, Chinese-English, WMT English{--}German and Opensubtitle English{--}Russian, demonstrate that using document graphs can significantly improve the translation quality. Extensive analysis verifies that the document graph is beneficial for capturing discourse phenomena.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xu-etal-2021-document-graph">
<titleInfo>
<title>Document Graph for Neural Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mingzhou</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liangyou</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Derek</namePart>
<namePart type="given">F</namePart>
<namePart type="family">Wong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qun</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lidia</namePart>
<namePart type="given">S</namePart>
<namePart type="family">Chao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marie-Francine</namePart>
<namePart type="family">Moens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="given">Wen-tau</namePart>
<namePart type="family">Yih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online and Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Previous works have shown that contextual information can improve the performance of neural machine translation (NMT). However, most existing document-level NMT methods failed to leverage contexts beyond a few set of previous sentences. How to make use of the whole document as global contexts is still a challenge. To address this issue, we hypothesize that a document can be represented as a graph that connects relevant contexts regardless of their distances. We employ several types of relations, including adjacency, syntactic dependency, lexical consistency, and coreference, to construct the document graph. Then, we incorporate both source and target graphs into the conventional Transformer architecture with graph convolutional networks. Experiments on various NMT benchmarks, including IWSLT English–French, Chinese-English, WMT English–German and Opensubtitle English–Russian, demonstrate that using document graphs can significantly improve the translation quality. Extensive analysis verifies that the document graph is beneficial for capturing discourse phenomena.</abstract>
<identifier type="citekey">xu-etal-2021-document-graph</identifier>
<identifier type="doi">10.18653/v1/2021.emnlp-main.663</identifier>
<location>
<url>https://aclanthology.org/2021.emnlp-main.663</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>8435</start>
<end>8448</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Document Graph for Neural Machine Translation
%A Xu, Mingzhou
%A Li, Liangyou
%A Wong, Derek F.
%A Liu, Qun
%A Chao, Lidia S.
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online and Punta Cana, Dominican Republic
%F xu-etal-2021-document-graph
%X Previous works have shown that contextual information can improve the performance of neural machine translation (NMT). However, most existing document-level NMT methods failed to leverage contexts beyond a few set of previous sentences. How to make use of the whole document as global contexts is still a challenge. To address this issue, we hypothesize that a document can be represented as a graph that connects relevant contexts regardless of their distances. We employ several types of relations, including adjacency, syntactic dependency, lexical consistency, and coreference, to construct the document graph. Then, we incorporate both source and target graphs into the conventional Transformer architecture with graph convolutional networks. Experiments on various NMT benchmarks, including IWSLT English–French, Chinese-English, WMT English–German and Opensubtitle English–Russian, demonstrate that using document graphs can significantly improve the translation quality. Extensive analysis verifies that the document graph is beneficial for capturing discourse phenomena.
%R 10.18653/v1/2021.emnlp-main.663
%U https://aclanthology.org/2021.emnlp-main.663
%U https://doi.org/10.18653/v1/2021.emnlp-main.663
%P 8435-8448
Markdown (Informal)
[Document Graph for Neural Machine Translation](https://aclanthology.org/2021.emnlp-main.663) (Xu et al., EMNLP 2021)
ACL
- Mingzhou Xu, Liangyou Li, Derek F. Wong, Qun Liu, and Lidia S. Chao. 2021. Document Graph for Neural Machine Translation. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 8435–8448, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.