<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="libang-etal-2024-mian">
    <titleInfo>
        <title>面向中文实体识别的Transformers模型句子级非对抗鲁棒性研究(On Sentence-level Non-adversarial Robustness of Chinese Named Entity Recognition with Transformers Model)</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Libang</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Peiyan</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sijia</namePart>
        <namePart type="family">Shen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <language>
        <languageTerm type="text">zho</languageTerm>
    </language>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 23rd Chinese National Conference on Computational Linguistics (Volume 1: Main Conference)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Sun</namePart>
            <namePart type="family">Maosong</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Liang</namePart>
            <namePart type="family">Jiye</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Han</namePart>
            <namePart type="family">Xianpei</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Liu</namePart>
            <namePart type="family">Zhiyuan</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">He</namePart>
            <namePart type="family">Yulan</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Chinese Information Processing Society of China</publisher>
            <place>
                <placeTerm type="text">Taiyuan, China</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>“基于Transformers的中文实体识别模型在标准实体识别基准测试中取得了卓越性能,其鲁棒性研究也受到了广泛关注。当前,中文实体识别模型在实际部署中所面临的句子级非对抗鲁棒性问题研究不足,该文针对该问题开展了研究。首先,该文从理论上分析并发现了Transformer中自注意力、相对位置嵌入及绝对位置嵌入对模型鲁棒性的负面影响。之后,提出了实体标签增强和滑动窗口约束的鲁棒性增强方法,并从理论上证明了提出方法能够提升Transformers模型的实体识别鲁棒性。最后,通过在3个中文数据集的实验,研究了4种基于Transformer的实体识别模型的脆弱性,所提出方法使模型的鲁棒性F1值提升最高可达4.95%。”</abstract>
    <identifier type="citekey">libang-etal-2024-mian</identifier>
    <location>
        <url>https://aclanthology.org/2024.ccl-1.73/</url>
    </location>
    <part>
        <date>2024-07</date>
        <extent unit="page">
            <start>941</start>
            <end>954</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T 面向中文实体识别的Transformers模型句子级非对抗鲁棒性研究(On Sentence-level Non-adversarial Robustness of Chinese Named Entity Recognition with Transformers Model)
%A Wang, Libang
%A Wang, Peiyan
%A Shen, Sijia
%Y Maosong, Sun
%Y Jiye, Liang
%Y Xianpei, Han
%Y Zhiyuan, Liu
%Y Yulan, He
%S Proceedings of the 23rd Chinese National Conference on Computational Linguistics (Volume 1: Main Conference)
%D 2024
%8 July
%I Chinese Information Processing Society of China
%C Taiyuan, China
%G zho
%F libang-etal-2024-mian
%X “基于Transformers的中文实体识别模型在标准实体识别基准测试中取得了卓越性能,其鲁棒性研究也受到了广泛关注。当前,中文实体识别模型在实际部署中所面临的句子级非对抗鲁棒性问题研究不足,该文针对该问题开展了研究。首先,该文从理论上分析并发现了Transformer中自注意力、相对位置嵌入及绝对位置嵌入对模型鲁棒性的负面影响。之后,提出了实体标签增强和滑动窗口约束的鲁棒性增强方法,并从理论上证明了提出方法能够提升Transformers模型的实体识别鲁棒性。最后,通过在3个中文数据集的实验,研究了4种基于Transformer的实体识别模型的脆弱性,所提出方法使模型的鲁棒性F1值提升最高可达4.95%。”
%U https://aclanthology.org/2024.ccl-1.73/
%P 941-954

Markdown (Informal)

[面向中文实体识别的Transformers模型句子级非对抗鲁棒性研究(On Sentence-level Non-adversarial Robustness of Chinese Named Entity Recognition with Transformers Model)](https://aclanthology.org/2024.ccl-1.73/) (Wang et al., CCL 2024)

• 面向中文实体识别的Transformers模型句子级非对抗鲁棒性研究(On Sentence-level Non-adversarial Robustness of Chinese Named Entity Recognition with Transformers Model) (Wang et al., CCL 2024)

ACL

• Libang Wang, Peiyan Wang, and Sijia Shen. 2024. 面向中文实体识别的Transformers模型句子级非对抗鲁棒性研究(On Sentence-level Non-adversarial Robustness of Chinese Named Entity Recognition with Transformers Model). In Proceedings of the 23rd Chinese National Conference on Computational Linguistics (Volume 1: Main Conference), pages 941–954, Taiyuan, China. Chinese Information Processing Society of China.