<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="su-etal-2022-ji">
    <titleInfo>
        <title>基于知识监督的标签降噪实体对齐(Refined De-noising for Labeled Entity Alignment from Auxiliary Evidence Knowledge)</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Fenglong</namePart>
        <namePart type="family">Su</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ning</namePart>
        <namePart type="family">Jing</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2022-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <language>
        <languageTerm type="text">Chinese</languageTerm>
        <languageTerm type="code" authority="iso639-2b">chi</languageTerm>
    </language>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 21st Chinese National Conference on Computational Linguistics</title>
        </titleInfo>
        <originInfo>
            <publisher>Chinese Information Processing Society of China</publisher>
            <place>
                <placeTerm type="text">Nanchang, China</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>“大多数现有的实体对齐解决方案都依赖于干净的标记数据来训练模型,很少关注种子噪声。为了解决实体对齐中的噪声问题,本文提出了一个标签降噪框架,在实体对齐中注入辅助知识和附带监督,以纠正标记和引导过程中的种子错误。特别是,考虑到以前基于邻域嵌入方法的弱点,本文应用了一种新的对偶关系注意力匹配编码器来加速知识图谱的结构学习,同时使用辅助知识来弥补结构表征的不足。然后,通过对抗训练来执行弱监督标签降噪。对于误差累积的问题,本文进一步使用对齐精化模块来提高模型的性能。实验结果表明,所提的框架能够轻松应对含噪声环境下的实体对齐问题,在多个真实数据集上的对齐准确性和噪声辨别能力始终优于其他基线方法。”</abstract>
    <identifier type="citekey">su-etal-2022-ji</identifier>
    <location>
        <url>https://aclanthology.org/2022.ccl-1.25</url>
    </location>
    <part>
        <date>2022-10</date>
        <extent unit="page">
            <start>268</start>
            <end>280</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T 基于知识监督的标签降噪实体对齐(Refined De-noising for Labeled Entity Alignment from Auxiliary Evidence Knowledge)
%A Su, Fenglong
%A Jing, Ning
%S Proceedings of the 21st Chinese National Conference on Computational Linguistics
%D 2022
%8 October
%I Chinese Information Processing Society of China
%C Nanchang, China
%G Chinese
%F su-etal-2022-ji
%X “大多数现有的实体对齐解决方案都依赖于干净的标记数据来训练模型,很少关注种子噪声。为了解决实体对齐中的噪声问题,本文提出了一个标签降噪框架,在实体对齐中注入辅助知识和附带监督,以纠正标记和引导过程中的种子错误。特别是,考虑到以前基于邻域嵌入方法的弱点,本文应用了一种新的对偶关系注意力匹配编码器来加速知识图谱的结构学习,同时使用辅助知识来弥补结构表征的不足。然后,通过对抗训练来执行弱监督标签降噪。对于误差累积的问题,本文进一步使用对齐精化模块来提高模型的性能。实验结果表明,所提的框架能够轻松应对含噪声环境下的实体对齐问题,在多个真实数据集上的对齐准确性和噪声辨别能力始终优于其他基线方法。”
%U https://aclanthology.org/2022.ccl-1.25
%P 268-280

Markdown (Informal)

[基于知识监督的标签降噪实体对齐(Refined De-noising for Labeled Entity Alignment from Auxiliary Evidence Knowledge)](https://aclanthology.org/2022.ccl-1.25) (Su & Jing, CCL 2022)

• 基于知识监督的标签降噪实体对齐(Refined De-noising for Labeled Entity Alignment from Auxiliary Evidence Knowledge) (Su & Jing, CCL 2022)

ACL

• Fenglong Su and Ning Jing. 2022. 基于知识监督的标签降噪实体对齐(Refined De-noising for Labeled Entity Alignment from Auxiliary Evidence Knowledge). In Proceedings of the 21st Chinese National Conference on Computational Linguistics, pages 268–280, Nanchang, China. Chinese Information Processing Society of China.