@inproceedings{yang-etal-2024-pga,
title = "{PGA}-{S}ci{RE}:基于大语言模型的数据增强框架进行科学领域的关系({PGA}-{S}ci{RE}:Harnessing {LLM} on Data Augmentation for Enhancing Scientific Relation Extraction)",
author = "Yang, Zhou and
Shimin, Dan and
Hongkui, Wei and
Zhehuan, Zhao and
Wenshuo, Feng",
editor = "Sun, Maosong and
Liang, Jiye and
Han, Xianpei and
Liu, Zhiyuan and
He, Yulan",
booktitle = "Proceedings of the 23rd Chinese National Conference on Computational Linguistics (Volume 1: Main Conference)",
month = jul,
year = "2024",
address = "Taiyuan, China",
publisher = "Chinese Information Processing Society of China",
url = "https://aclanthology.org/2024.ccl-1.27/",
pages = "352--369",
language = "zho",
abstract = "{\textquotedblleft}关系提取旨在识别文本中提到的实体对之间的关系。大语言模型的进步对自然语言处理任务产生了巨大的影响。在这项工作中,我们针对科学领域的关系抽取任务,提出一个名为PGA的数据增强框架,用于提升模型在科学领域的关系抽取的性能。框架引入了两种数据增强的方式,利用大语言模型通过转述原训练集样本,得到句意相同但具备不同表述和形式的伪样本。以及指导大语言模型根据原训练集样本的关系和实体标签,生成暗含对应标签信息的句子。这两种伪样本分别与原数据集共同参与关系抽取模型的训练。实验中PGA框架提高了三个主流模型的科学领域内关系抽取的F1分数。同时,使用大语言模型获得样本也能有效减少人工标注数据的成本。{\textquotedblright}"
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-etal-2024-pga">
<titleInfo>
<title>PGA-SciRE:基于大语言模型的数据增强框架进行科学领域的关系(PGA-SciRE:Harnessing LLM on Data Augmentation for Enhancing Scientific Relation Extraction)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhou</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dan</namePart>
<namePart type="family">Shimin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Hongkui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhao</namePart>
<namePart type="family">Zhehuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Feng</namePart>
<namePart type="family">Wenshuo</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">Maosong</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiye</namePart>
<namePart type="family">Liang</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>
<name type="personal">
<namePart type="given">Zhiyuan</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</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>“关系提取旨在识别文本中提到的实体对之间的关系。大语言模型的进步对自然语言处理任务产生了巨大的影响。在这项工作中,我们针对科学领域的关系抽取任务,提出一个名为PGA的数据增强框架,用于提升模型在科学领域的关系抽取的性能。框架引入了两种数据增强的方式,利用大语言模型通过转述原训练集样本,得到句意相同但具备不同表述和形式的伪样本。以及指导大语言模型根据原训练集样本的关系和实体标签,生成暗含对应标签信息的句子。这两种伪样本分别与原数据集共同参与关系抽取模型的训练。实验中PGA框架提高了三个主流模型的科学领域内关系抽取的F1分数。同时,使用大语言模型获得样本也能有效减少人工标注数据的成本。”</abstract>
<identifier type="citekey">yang-etal-2024-pga</identifier>
<location>
<url>https://aclanthology.org/2024.ccl-1.27/</url>
</location>
<part>
<date>2024-07</date>
<extent unit="page">
<start>352</start>
<end>369</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PGA-SciRE:基于大语言模型的数据增强框架进行科学领域的关系(PGA-SciRE:Harnessing LLM on Data Augmentation for Enhancing Scientific Relation Extraction)
%A Yang, Zhou
%A Shimin, Dan
%A Hongkui, Wei
%A Zhehuan, Zhao
%A Wenshuo, Feng
%Y Sun, Maosong
%Y Liang, Jiye
%Y Han, Xianpei
%Y Liu, Zhiyuan
%Y He, Yulan
%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 yang-etal-2024-pga
%X “关系提取旨在识别文本中提到的实体对之间的关系。大语言模型的进步对自然语言处理任务产生了巨大的影响。在这项工作中,我们针对科学领域的关系抽取任务,提出一个名为PGA的数据增强框架,用于提升模型在科学领域的关系抽取的性能。框架引入了两种数据增强的方式,利用大语言模型通过转述原训练集样本,得到句意相同但具备不同表述和形式的伪样本。以及指导大语言模型根据原训练集样本的关系和实体标签,生成暗含对应标签信息的句子。这两种伪样本分别与原数据集共同参与关系抽取模型的训练。实验中PGA框架提高了三个主流模型的科学领域内关系抽取的F1分数。同时,使用大语言模型获得样本也能有效减少人工标注数据的成本。”
%U https://aclanthology.org/2024.ccl-1.27/
%P 352-369
Markdown (Informal)
[PGA-SciRE:基于大语言模型的数据增强框架进行科学领域的关系(PGA-SciRE:Harnessing LLM on Data Augmentation for Enhancing Scientific Relation Extraction)](https://aclanthology.org/2024.ccl-1.27/) (Yang et al., CCL 2024)
ACL