@inproceedings{li-etal-2023-ccl23,
title = "{CCL}23-Eval 任务1系统报告:基于增量预训练与对抗学习的古籍命名实体识别(System Report for {CCL}23-Eval Task 1:::{G}u{NER} Based on Incremental Pretraining and Adversarial Learning)",
author = "Li, Jianlong and
Yu, Youren and
Liu, Xueyang and
Zhu, Siwen",
editor = "Sun, Maosong and
Qin, Bing and
Qiu, Xipeng and
Jiang, Jing and
Han, Xianpei",
booktitle = "Proceedings of the 22nd Chinese National Conference on Computational Linguistics (Volume 3: Evaluations)",
month = aug,
year = "2023",
address = "Harbin, China",
publisher = "Chinese Information Processing Society of China",
url = "https://aclanthology.org/2023.ccl-3.3",
pages = "23--33",
abstract = "{``}古籍命名实体识别是正确分析处理古汉语文本的基础步骤,也是深度挖掘、组织人文知识的重要前提。古汉语信息熵高、艰涩难懂,因此该领域技术研究进展缓慢。针对现有实体识别模型抗干扰能力差、实体边界识别不准确的问题,本文提出使用NEZHA-TCN与全局指针相结合的方式进行古籍命名实体识别。同时构建了一套古文数据集,该数据集包含正史中各种古籍文本,共87M,397,995条文本,用于NEZHA-TCN模型的增量预训练。在模型训练过程中,为了增强模型的抗干扰能力,引入快速梯度法对词嵌入层添加干扰。实验结果表明,本文提出的方法能够有效挖掘潜藏在古籍文本中的实体信息,F1值为95.34{\%}。{''}",
language = "Chinese",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2023-ccl23">
<titleInfo>
<title>CCL23-Eval 任务1系统报告:基于增量预训练与对抗学习的古籍命名实体识别(System Report for CCL23-Eval Task 1:::GuNER Based on Incremental Pretraining and Adversarial Learning)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jianlong</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Youren</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xueyang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siwen</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-08</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 22nd Chinese National Conference on Computational Linguistics (Volume 3: Evaluations)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maosong</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bing</namePart>
<namePart type="family">Qin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xipeng</namePart>
<namePart type="family">Qiu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xianpei</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Chinese Information Processing Society of China</publisher>
<place>
<placeTerm type="text">Harbin, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>“古籍命名实体识别是正确分析处理古汉语文本的基础步骤,也是深度挖掘、组织人文知识的重要前提。古汉语信息熵高、艰涩难懂,因此该领域技术研究进展缓慢。针对现有实体识别模型抗干扰能力差、实体边界识别不准确的问题,本文提出使用NEZHA-TCN与全局指针相结合的方式进行古籍命名实体识别。同时构建了一套古文数据集,该数据集包含正史中各种古籍文本,共87M,397,995条文本,用于NEZHA-TCN模型的增量预训练。在模型训练过程中,为了增强模型的抗干扰能力,引入快速梯度法对词嵌入层添加干扰。实验结果表明,本文提出的方法能够有效挖掘潜藏在古籍文本中的实体信息,F1值为95.34%。”</abstract>
<identifier type="citekey">li-etal-2023-ccl23</identifier>
<location>
<url>https://aclanthology.org/2023.ccl-3.3</url>
</location>
<part>
<date>2023-08</date>
<extent unit="page">
<start>23</start>
<end>33</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CCL23-Eval 任务1系统报告:基于增量预训练与对抗学习的古籍命名实体识别(System Report for CCL23-Eval Task 1:::GuNER Based on Incremental Pretraining and Adversarial Learning)
%A Li, Jianlong
%A Yu, Youren
%A Liu, Xueyang
%A Zhu, Siwen
%Y Sun, Maosong
%Y Qin, Bing
%Y Qiu, Xipeng
%Y Jiang, Jing
%Y Han, Xianpei
%S Proceedings of the 22nd Chinese National Conference on Computational Linguistics (Volume 3: Evaluations)
%D 2023
%8 August
%I Chinese Information Processing Society of China
%C Harbin, China
%G Chinese
%F li-etal-2023-ccl23
%X “古籍命名实体识别是正确分析处理古汉语文本的基础步骤,也是深度挖掘、组织人文知识的重要前提。古汉语信息熵高、艰涩难懂,因此该领域技术研究进展缓慢。针对现有实体识别模型抗干扰能力差、实体边界识别不准确的问题,本文提出使用NEZHA-TCN与全局指针相结合的方式进行古籍命名实体识别。同时构建了一套古文数据集,该数据集包含正史中各种古籍文本,共87M,397,995条文本,用于NEZHA-TCN模型的增量预训练。在模型训练过程中,为了增强模型的抗干扰能力,引入快速梯度法对词嵌入层添加干扰。实验结果表明,本文提出的方法能够有效挖掘潜藏在古籍文本中的实体信息,F1值为95.34%。”
%U https://aclanthology.org/2023.ccl-3.3
%P 23-33
Markdown (Informal)
[CCL23-Eval 任务1系统报告:基于增量预训练与对抗学习的古籍命名实体识别(System Report for CCL23-Eval Task 1:::GuNER Based on Incremental Pretraining and Adversarial Learning)](https://aclanthology.org/2023.ccl-3.3) (Li et al., CCL 2023)
ACL