@inproceedings{huang-etal-2023-ccl23-eval,
title = "{CCL}23-Eval 任务6系统报告:基于预训练语言模型的双策略分类优化算法(System Report for {CCL}23-Eval Task 6:Double-strategy classification optimization algorithm based on pre-training language model)",
author = "Huang, Yongqing and
Yang, Hailong and
Xuelin, Fu",
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-3.20",
pages = "184--192",
abstract = "{``}诈骗案件分类问题是打击电信网络诈骗犯罪过程中的关键一环,根据不同的诈骗方式、手法等将其分类,通过对不同案件进行有效分类能够便于统计现状,有助于公安部门掌握当前电信网络诈骗案件的分布特点,进而能够对不同类别的诈骗案件作出针对性的预防、监管、制止、侦查等措施。诈骗案件分类属于自然语言处理领域的文本分类任务,传统的基于LSTM和CNN等分类模型能在起到一定的效果,但是由于它们模型结构的参数量的限制,难以达到较为理想的效果。本文基于预训练语言模型Nezha,结合对抗扰动和指数移动平均策略,有助于电信网络诈骗案件分类任务取得更好效果,充分利用电信网络诈骗案件的数据。我们队伍未采用多模型融合的方法,并最终在此次评测任务中排名第三,评测指标分数为0.8625。{''}",
language = "Chinese",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="huang-etal-2023-ccl23-eval">
<titleInfo>
<title>CCL23-Eval 任务6系统报告:基于预训练语言模型的双策略分类优化算法(System Report for CCL23-Eval Task 6:Double-strategy classification optimization algorithm based on pre-training language model)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yongqing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hailong</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fu</namePart>
<namePart type="family">Xuelin</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>“诈骗案件分类问题是打击电信网络诈骗犯罪过程中的关键一环,根据不同的诈骗方式、手法等将其分类,通过对不同案件进行有效分类能够便于统计现状,有助于公安部门掌握当前电信网络诈骗案件的分布特点,进而能够对不同类别的诈骗案件作出针对性的预防、监管、制止、侦查等措施。诈骗案件分类属于自然语言处理领域的文本分类任务,传统的基于LSTM和CNN等分类模型能在起到一定的效果,但是由于它们模型结构的参数量的限制,难以达到较为理想的效果。本文基于预训练语言模型Nezha,结合对抗扰动和指数移动平均策略,有助于电信网络诈骗案件分类任务取得更好效果,充分利用电信网络诈骗案件的数据。我们队伍未采用多模型融合的方法,并最终在此次评测任务中排名第三,评测指标分数为0.8625。”</abstract>
<identifier type="citekey">huang-etal-2023-ccl23-eval</identifier>
<location>
<url>https://aclanthology.org/2023.ccl-3.20</url>
</location>
<part>
<date>2023-08</date>
<extent unit="page">
<start>184</start>
<end>192</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CCL23-Eval 任务6系统报告:基于预训练语言模型的双策略分类优化算法(System Report for CCL23-Eval Task 6:Double-strategy classification optimization algorithm based on pre-training language model)
%A Huang, Yongqing
%A Yang, Hailong
%A Xuelin, Fu
%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 huang-etal-2023-ccl23-eval
%X “诈骗案件分类问题是打击电信网络诈骗犯罪过程中的关键一环,根据不同的诈骗方式、手法等将其分类,通过对不同案件进行有效分类能够便于统计现状,有助于公安部门掌握当前电信网络诈骗案件的分布特点,进而能够对不同类别的诈骗案件作出针对性的预防、监管、制止、侦查等措施。诈骗案件分类属于自然语言处理领域的文本分类任务,传统的基于LSTM和CNN等分类模型能在起到一定的效果,但是由于它们模型结构的参数量的限制,难以达到较为理想的效果。本文基于预训练语言模型Nezha,结合对抗扰动和指数移动平均策略,有助于电信网络诈骗案件分类任务取得更好效果,充分利用电信网络诈骗案件的数据。我们队伍未采用多模型融合的方法,并最终在此次评测任务中排名第三,评测指标分数为0.8625。”
%U https://aclanthology.org/2023.ccl-3.20
%P 184-192
Markdown (Informal)
[CCL23-Eval 任务6系统报告:基于预训练语言模型的双策略分类优化算法(System Report for CCL23-Eval Task 6:Double-strategy classification optimization algorithm based on pre-training language model)](https://aclanthology.org/2023.ccl-3.20) (Huang et al., CCL 2023)
ACL