<?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>
        <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
%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)

• Multi-level Community-awareness Graph Neural Networks for Neural Machine Translation (Nguyen et al., COLING 2022)

ACL

• Binh Nguyen, Long Nguyen, and Dien Dinh. 2022. Multi-level Community-awareness Graph Neural Networks for Neural Machine Translation. In Proceedings of the 29th International Conference on Computational Linguistics, pages 5021–5028, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.