<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="han-shareghi-2022-self">
    <titleInfo>
        <title>Self-supervised Graph Masking Pre-training for Graph-to-Text Generation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jiuzhou</namePart>
        <namePart type="family">Han</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ehsan</namePart>
        <namePart type="family">Shareghi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2022-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yoav</namePart>
            <namePart type="family">Goldberg</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Zornitsa</namePart>
            <namePart type="family">Kozareva</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yue</namePart>
            <namePart type="family">Zhang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Large-scale pre-trained language models (PLMs) have advanced Graph-to-Text (G2T) generation by processing the linearised version of a graph. However, the linearisation is known to ignore the structural information. Additionally, PLMs are typically pre-trained on free text which introduces domain mismatch between pre-training and downstream G2T generation tasks. To address these shortcomings, we propose graph masking pre-training strategies that neither require supervision signals nor adjust the architecture of the underlying pre-trained encoder-decoder model. When used with a pre-trained T5, our approach achieves new state-of-the-art results on WebNLG+2020 and EventNarrative G2T generation datasets. Our method also shows to be very effective in the low-resource setting.</abstract>
    <identifier type="citekey">han-shareghi-2022-self</identifier>
    <identifier type="doi">10.18653/v1/2022.emnlp-main.321</identifier>
    <location>
        <url>https://aclanthology.org/2022.emnlp-main.321</url>
    </location>
    <part>
        <date>2022-12</date>
        <extent unit="page">
            <start>4845</start>
            <end>4853</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Self-supervised Graph Masking Pre-training for Graph-to-Text Generation
%A Han, Jiuzhou
%A Shareghi, Ehsan
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F han-shareghi-2022-self
%X Large-scale pre-trained language models (PLMs) have advanced Graph-to-Text (G2T) generation by processing the linearised version of a graph. However, the linearisation is known to ignore the structural information. Additionally, PLMs are typically pre-trained on free text which introduces domain mismatch between pre-training and downstream G2T generation tasks. To address these shortcomings, we propose graph masking pre-training strategies that neither require supervision signals nor adjust the architecture of the underlying pre-trained encoder-decoder model. When used with a pre-trained T5, our approach achieves new state-of-the-art results on WebNLG+2020 and EventNarrative G2T generation datasets. Our method also shows to be very effective in the low-resource setting.
%R 10.18653/v1/2022.emnlp-main.321
%U https://aclanthology.org/2022.emnlp-main.321
%U https://doi.org/10.18653/v1/2022.emnlp-main.321
%P 4845-4853

Markdown (Informal)

[Self-supervised Graph Masking Pre-training for Graph-to-Text Generation](https://aclanthology.org/2022.emnlp-main.321) (Han & Shareghi, EMNLP 2022)

• Self-supervised Graph Masking Pre-training for Graph-to-Text Generation (Han & Shareghi, EMNLP 2022)

ACL

• Jiuzhou Han and Ehsan Shareghi. 2022. Self-supervised Graph Masking Pre-training for Graph-to-Text Generation. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 4845–4853, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.