@inproceedings{rongbo-etal-2024-mian,
title = "面向中文抽象语义表示解析的大模型评估与增强",
author = "Rongbo, Chen and
Zhenwu, Pei and
Xuefeng, Bai and
Kehai, Chen and
Min, Zhang",
editor = "Lin, Hongfei and
Tan, Hongye and
Li, Bin",
booktitle = "Proceedings of the 23rd Chinese National Conference on Computational Linguistics (Volume 3: Evaluations)",
month = jul,
year = "2024",
address = "Taiyuan, China",
publisher = "Chinese Information Processing Society of China",
url = "https://aclanthology.org/2024.ccl-3.15/",
pages = "135--142",
language = "zho",
abstract = "{\textquotedblleft}本文介绍了我们在第二十三届中文计算语言学大会中文抽象语义表示解析评测任务中提交的参赛系统。中文抽象语义表示(Chinese Abstract Meaning Representa-tion,CAMR)以一个单根可遍历的有向无环图表示中文句子的语义。本系统选择大语言模型作为解决方案。我们首先系统地评估了当下中文大语言模型在AMR解析任务上的性能,在此基础上基于图融合算法整合性能较高的大模型预测结果,最终得到预测的CAMR图。实验结果表明,1)现有大模型已经具备一定的少样本中文AMR解析能力;2)基于微调中文大模型的AMR解析系统能够取得相较以往最优系统更强的性能;3)图融合算法能够进一步增强基于大模型的CAMR解析系统的性能。{\textquotedblright}"
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rongbo-etal-2024-mian">
<titleInfo>
<title>面向中文抽象语义表示解析的大模型评估与增强</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chen</namePart>
<namePart type="family">Rongbo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pei</namePart>
<namePart type="family">Zhenwu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bai</namePart>
<namePart type="family">Xuefeng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chen</namePart>
<namePart type="family">Kehai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhang</namePart>
<namePart type="family">Min</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 3: Evaluations)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hongfei</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongye</namePart>
<namePart type="family">Tan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bin</namePart>
<namePart type="family">Li</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>“本文介绍了我们在第二十三届中文计算语言学大会中文抽象语义表示解析评测任务中提交的参赛系统。中文抽象语义表示(Chinese Abstract Meaning Representa-tion,CAMR)以一个单根可遍历的有向无环图表示中文句子的语义。本系统选择大语言模型作为解决方案。我们首先系统地评估了当下中文大语言模型在AMR解析任务上的性能,在此基础上基于图融合算法整合性能较高的大模型预测结果,最终得到预测的CAMR图。实验结果表明,1)现有大模型已经具备一定的少样本中文AMR解析能力;2)基于微调中文大模型的AMR解析系统能够取得相较以往最优系统更强的性能;3)图融合算法能够进一步增强基于大模型的CAMR解析系统的性能。”</abstract>
<identifier type="citekey">rongbo-etal-2024-mian</identifier>
<location>
<url>https://aclanthology.org/2024.ccl-3.15/</url>
</location>
<part>
<date>2024-07</date>
<extent unit="page">
<start>135</start>
<end>142</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T 面向中文抽象语义表示解析的大模型评估与增强
%A Rongbo, Chen
%A Zhenwu, Pei
%A Xuefeng, Bai
%A Kehai, Chen
%A Min, Zhang
%Y Lin, Hongfei
%Y Tan, Hongye
%Y Li, Bin
%S Proceedings of the 23rd Chinese National Conference on Computational Linguistics (Volume 3: Evaluations)
%D 2024
%8 July
%I Chinese Information Processing Society of China
%C Taiyuan, China
%G zho
%F rongbo-etal-2024-mian
%X “本文介绍了我们在第二十三届中文计算语言学大会中文抽象语义表示解析评测任务中提交的参赛系统。中文抽象语义表示(Chinese Abstract Meaning Representa-tion,CAMR)以一个单根可遍历的有向无环图表示中文句子的语义。本系统选择大语言模型作为解决方案。我们首先系统地评估了当下中文大语言模型在AMR解析任务上的性能,在此基础上基于图融合算法整合性能较高的大模型预测结果,最终得到预测的CAMR图。实验结果表明,1)现有大模型已经具备一定的少样本中文AMR解析能力;2)基于微调中文大模型的AMR解析系统能够取得相较以往最优系统更强的性能;3)图融合算法能够进一步增强基于大模型的CAMR解析系统的性能。”
%U https://aclanthology.org/2024.ccl-3.15/
%P 135-142
Markdown (Informal)
[面向中文抽象语义表示解析的大模型评估与增强](https://aclanthology.org/2024.ccl-3.15/) (Rongbo et al., CCL 2024)
ACL
- Chen Rongbo, Pei Zhenwu, Bai Xuefeng, Chen Kehai, and Zhang Min. 2024. 面向中文抽象语义表示解析的大模型评估与增强. In Proceedings of the 23rd Chinese National Conference on Computational Linguistics (Volume 3: Evaluations), pages 135–142, Taiyuan, China. Chinese Information Processing Society of China.