@inproceedings{nguyen-etal-2022-multi,
title = "Multi-level Community-awareness Graph Neural Networks for Neural Machine Translation",
author = "Nguyen, Binh and
Nguyen, Long and
Dinh, Dien",
editor = "Calzolari, Nicoletta and
Huang, Chu-Ren and
Kim, Hansaem and
Pustejovsky, James and
Wanner, Leo and
Choi, Key-Sun and
Ryu, Pum-Mo and
Chen, Hsin-Hsi and
Donatelli, Lucia and
Ji, Heng and
Kurohashi, Sadao and
Paggio, Patrizia and
Xue, Nianwen and
Kim, Seokhwan and
Hahm, Younggyun and
He, Zhong and
Lee, Tony Kyungil and
Santus, Enrico and
Bond, Francis and
Na, Seung-Hoon",
booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2022.coling-1.444",
pages = "5021--5028",
abstract = "Neural Machine Translation (NMT) aims to translate the source- to the target-language while preserving the original meaning. Linguistic information such as morphology, syntactic, and semantics shall be grasped in token embeddings to produce a high-quality translation. Recent works have leveraged the powerful Graph Neural Networks (GNNs) to encode such language knowledge into token embeddings. Specifically, they use a trained parser to construct semantic graphs given sentences and then apply GNNs. However, most semantic graphs are tree-shaped and too sparse for GNNs which cause the over-smoothing problem. To alleviate this problem, we propose a novel Multi-level Community-awareness Graph Neural Network (MC-GNN) layer to jointly model local and global relationships between words and their linguistic roles in multiple communities. Intuitively, the MC-GNN layer substitutes a self-attention layer at the encoder side of a transformer-based machine translation model. Extensive experiments on four language-pair datasets with common evaluation metrics show the remarkable improvements of our method while reducing the time complexity in very long sentences.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nguyen-etal-2022-multi">
<titleInfo>
<title>Multi-level Community-awareness Graph Neural Networks for Neural Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Binh</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Long</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dien</namePart>
<namePart type="family">Dinh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 29th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chu-Ren</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hansaem</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Pustejovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Key-Sun</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pum-Mo</namePart>
<namePart type="family">Ryu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsin-Hsi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Donatelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sadao</namePart>
<namePart type="family">Kurohashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrizia</namePart>
<namePart type="family">Paggio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seokhwan</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Younggyun</namePart>
<namePart type="family">Hahm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhong</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tony</namePart>
<namePart type="given">Kyungil</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrico</namePart>
<namePart type="family">Santus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Bond</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seung-Hoon</namePart>
<namePart type="family">Na</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Neural Machine Translation (NMT) aims to translate the source- to the target-language while preserving the original meaning. Linguistic information such as morphology, syntactic, and semantics shall be grasped in token embeddings to produce a high-quality translation. Recent works have leveraged the powerful Graph Neural Networks (GNNs) to encode such language knowledge into token embeddings. Specifically, they use a trained parser to construct semantic graphs given sentences and then apply GNNs. However, most semantic graphs are tree-shaped and too sparse for GNNs which cause the over-smoothing problem. To alleviate this problem, we propose a novel Multi-level Community-awareness Graph Neural Network (MC-GNN) layer to jointly model local and global relationships between words and their linguistic roles in multiple communities. Intuitively, the MC-GNN layer substitutes a self-attention layer at the encoder side of a transformer-based machine translation model. Extensive experiments on four language-pair datasets with common evaluation metrics show the remarkable improvements of our method while reducing the time complexity in very long sentences.</abstract>
<identifier type="citekey">nguyen-etal-2022-multi</identifier>
<location>
<url>https://aclanthology.org/2022.coling-1.444</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>5021</start>
<end>5028</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multi-level Community-awareness Graph Neural Networks for Neural Machine Translation
%A Nguyen, Binh
%A Nguyen, Long
%A Dinh, Dien
%Y Calzolari, Nicoletta
%Y Huang, Chu-Ren
%Y Kim, Hansaem
%Y Pustejovsky, James
%Y Wanner, Leo
%Y Choi, Key-Sun
%Y Ryu, Pum-Mo
%Y Chen, Hsin-Hsi
%Y Donatelli, Lucia
%Y Ji, Heng
%Y Kurohashi, Sadao
%Y Paggio, Patrizia
%Y Xue, Nianwen
%Y Kim, Seokhwan
%Y Hahm, Younggyun
%Y He, Zhong
%Y Lee, Tony Kyungil
%Y Santus, Enrico
%Y Bond, Francis
%Y Na, Seung-Hoon
%S Proceedings of the 29th International Conference on Computational Linguistics
%D 2022
%8 October
%I International Committee on Computational Linguistics
%C Gyeongju, Republic of Korea
%F nguyen-etal-2022-multi
%X Neural Machine Translation (NMT) aims to translate the source- to the target-language while preserving the original meaning. Linguistic information such as morphology, syntactic, and semantics shall be grasped in token embeddings to produce a high-quality translation. Recent works have leveraged the powerful Graph Neural Networks (GNNs) to encode such language knowledge into token embeddings. Specifically, they use a trained parser to construct semantic graphs given sentences and then apply GNNs. However, most semantic graphs are tree-shaped and too sparse for GNNs which cause the over-smoothing problem. To alleviate this problem, we propose a novel Multi-level Community-awareness Graph Neural Network (MC-GNN) layer to jointly model local and global relationships between words and their linguistic roles in multiple communities. Intuitively, the MC-GNN layer substitutes a self-attention layer at the encoder side of a transformer-based machine translation model. Extensive experiments on four language-pair datasets with common evaluation metrics show the remarkable improvements of our method while reducing the time complexity in very long sentences.
%U https://aclanthology.org/2022.coling-1.444
%P 5021-5028
Markdown (Informal)
[Multi-level Community-awareness Graph Neural Networks for Neural Machine Translation](https://aclanthology.org/2022.coling-1.444) (Nguyen et al., COLING 2022)
ACL