@inproceedings{xie-etal-2022-gu,
title = "古汉语嵌套命名实体识别数据集的构建和应用研究(Construction and application of classical {C}hinese nested named entity recognition data set)",
author = "Xie, Zhiqiang and
Liu, Jinzhu and
Liu, Genhui",
editor = "Sun, Maosong and
Liu, Yang and
Che, Wanxiang and
Feng, Yang and
Qiu, Xipeng and
Rao, Gaoqi and
Chen, Yubo",
booktitle = "Proceedings of the 21st Chinese National Conference on Computational Linguistics",
month = oct,
year = "2022",
address = "Nanchang, China",
publisher = "Chinese Information Processing Society of China",
url = "https://aclanthology.org/2022.ccl-1.37",
pages = "406--416",
abstract = "{``}本文聚焦研究较少的古汉语嵌套命名实体识别任务,以《史记》作为原始语料,针对古文意义丰富而导致的实体分类模糊问题,分别构建了基于字词本义和语境义2个标注标准的古汉语嵌套命名实体数据集,探讨了数据集的实体分类原则和标注格式,并用RoBERTa-classical-chinese+GlobalPointer模型进行对比试验,标准一数据集F1值为80.42{\%},标准二F1值为77.43{\%},以此确定了数据集的标注标准。之后对比了六种预训练模型配合GlobalPointer在古汉语嵌套命名实体识别任务上的表现。最终试验结果:RoBERTa-classical-chinese模型F1值为84.71{\%},表现最好。{''}",
language = "Chinese",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xie-etal-2022-gu">
<titleInfo>
<title>古汉语嵌套命名实体识别数据集的构建和应用研究(Construction and application of classical Chinese nested named entity recognition data set)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhiqiang</namePart>
<namePart type="family">Xie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinzhu</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Genhui</namePart>
<namePart type="family">Liu</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>
<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">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Feng</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">Gaoqi</namePart>
<namePart type="family">Rao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yubo</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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>“本文聚焦研究较少的古汉语嵌套命名实体识别任务,以《史记》作为原始语料,针对古文意义丰富而导致的实体分类模糊问题,分别构建了基于字词本义和语境义2个标注标准的古汉语嵌套命名实体数据集,探讨了数据集的实体分类原则和标注格式,并用RoBERTa-classical-chinese+GlobalPointer模型进行对比试验,标准一数据集F1值为80.42%,标准二F1值为77.43%,以此确定了数据集的标注标准。之后对比了六种预训练模型配合GlobalPointer在古汉语嵌套命名实体识别任务上的表现。最终试验结果:RoBERTa-classical-chinese模型F1值为84.71%,表现最好。”</abstract>
<identifier type="citekey">xie-etal-2022-gu</identifier>
<location>
<url>https://aclanthology.org/2022.ccl-1.37</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>406</start>
<end>416</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T 古汉语嵌套命名实体识别数据集的构建和应用研究(Construction and application of classical Chinese nested named entity recognition data set)
%A Xie, Zhiqiang
%A Liu, Jinzhu
%A Liu, Genhui
%Y Sun, Maosong
%Y Liu, Yang
%Y Che, Wanxiang
%Y Feng, Yang
%Y Qiu, Xipeng
%Y Rao, Gaoqi
%Y Chen, Yubo
%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 xie-etal-2022-gu
%X “本文聚焦研究较少的古汉语嵌套命名实体识别任务,以《史记》作为原始语料,针对古文意义丰富而导致的实体分类模糊问题,分别构建了基于字词本义和语境义2个标注标准的古汉语嵌套命名实体数据集,探讨了数据集的实体分类原则和标注格式,并用RoBERTa-classical-chinese+GlobalPointer模型进行对比试验,标准一数据集F1值为80.42%,标准二F1值为77.43%,以此确定了数据集的标注标准。之后对比了六种预训练模型配合GlobalPointer在古汉语嵌套命名实体识别任务上的表现。最终试验结果:RoBERTa-classical-chinese模型F1值为84.71%,表现最好。”
%U https://aclanthology.org/2022.ccl-1.37
%P 406-416
Markdown (Informal)
[古汉语嵌套命名实体识别数据集的构建和应用研究(Construction and application of classical Chinese nested named entity recognition data set)](https://aclanthology.org/2022.ccl-1.37) (Xie et al., CCL 2022)
ACL