@inproceedings{sun-etal-2023-da,
title = "大规模语言模型增强的中文篇章多维度阅读体验量化研究(Quantitative Research on Multi-dimensional Reading Experience of {C}hinese Texts Enhanced by Large Language Model)",
author = "Sun, Jiadai and
Tang, Siyi and
Wang, Shike and
Yu, Dong and
Liu, Pengyuan",
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",
month = aug,
year = "2023",
address = "Harbin, China",
publisher = "Chinese Information Processing Society of China",
url = "https://aclanthology.org/2023.ccl-1.32",
pages = "364--376",
abstract = "{``}现有的文本分级阅读研究往往从文本可读性的角度出发,以离散的文本难度等级的形式为读者推荐阅读书目。目前,仍缺少一种研究读者在阅读过程中产生的多方面、深层次阅读体验的体系结构。对此,我们调研了读者在阅读中文篇章过程中产生的不同阅读体验,提出了中文篇章多维度阅读体验的量化体系。我们将阅读过程中呈现的连续性的阅读体验归纳为多种类别,并在此基础上构建了中文篇章多维度阅读体验数据集。同时,我们探究了以大规模语言模型为基础的ChatGPT对阅读体验的量化能力,发现其虽具备强大的信息抽取和语义理解能力,在阅读体验的量化上却表现不佳。但我们发现大规模语言模型所蕴含的能力能够以知识蒸馏的方式协助深层属性的量化,基于此,我们实现了大规模语言模型增强的中文篇章多维阅读体验量化模型。模型在各维度阅读体验上的平均F1值达到0.72,高于ChatGPT的Fewshot结果0.48。{''}",
language = "Chinese",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sun-etal-2023-da">
<titleInfo>
<title>大规模语言模型增强的中文篇章多维度阅读体验量化研究(Quantitative Research on Multi-dimensional Reading Experience of Chinese Texts Enhanced by Large Language Model)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jiadai</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siyi</namePart>
<namePart type="family">Tang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shike</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dong</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pengyuan</namePart>
<namePart type="family">Liu</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</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>“现有的文本分级阅读研究往往从文本可读性的角度出发,以离散的文本难度等级的形式为读者推荐阅读书目。目前,仍缺少一种研究读者在阅读过程中产生的多方面、深层次阅读体验的体系结构。对此,我们调研了读者在阅读中文篇章过程中产生的不同阅读体验,提出了中文篇章多维度阅读体验的量化体系。我们将阅读过程中呈现的连续性的阅读体验归纳为多种类别,并在此基础上构建了中文篇章多维度阅读体验数据集。同时,我们探究了以大规模语言模型为基础的ChatGPT对阅读体验的量化能力,发现其虽具备强大的信息抽取和语义理解能力,在阅读体验的量化上却表现不佳。但我们发现大规模语言模型所蕴含的能力能够以知识蒸馏的方式协助深层属性的量化,基于此,我们实现了大规模语言模型增强的中文篇章多维阅读体验量化模型。模型在各维度阅读体验上的平均F1值达到0.72,高于ChatGPT的Fewshot结果0.48。”</abstract>
<identifier type="citekey">sun-etal-2023-da</identifier>
<location>
<url>https://aclanthology.org/2023.ccl-1.32</url>
</location>
<part>
<date>2023-08</date>
<extent unit="page">
<start>364</start>
<end>376</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T 大规模语言模型增强的中文篇章多维度阅读体验量化研究(Quantitative Research on Multi-dimensional Reading Experience of Chinese Texts Enhanced by Large Language Model)
%A Sun, Jiadai
%A Tang, Siyi
%A Wang, Shike
%A Yu, Dong
%A Liu, Pengyuan
%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
%D 2023
%8 August
%I Chinese Information Processing Society of China
%C Harbin, China
%G Chinese
%F sun-etal-2023-da
%X “现有的文本分级阅读研究往往从文本可读性的角度出发,以离散的文本难度等级的形式为读者推荐阅读书目。目前,仍缺少一种研究读者在阅读过程中产生的多方面、深层次阅读体验的体系结构。对此,我们调研了读者在阅读中文篇章过程中产生的不同阅读体验,提出了中文篇章多维度阅读体验的量化体系。我们将阅读过程中呈现的连续性的阅读体验归纳为多种类别,并在此基础上构建了中文篇章多维度阅读体验数据集。同时,我们探究了以大规模语言模型为基础的ChatGPT对阅读体验的量化能力,发现其虽具备强大的信息抽取和语义理解能力,在阅读体验的量化上却表现不佳。但我们发现大规模语言模型所蕴含的能力能够以知识蒸馏的方式协助深层属性的量化,基于此,我们实现了大规模语言模型增强的中文篇章多维阅读体验量化模型。模型在各维度阅读体验上的平均F1值达到0.72,高于ChatGPT的Fewshot结果0.48。”
%U https://aclanthology.org/2023.ccl-1.32
%P 364-376
Markdown (Informal)
[大规模语言模型增强的中文篇章多维度阅读体验量化研究(Quantitative Research on Multi-dimensional Reading Experience of Chinese Texts Enhanced by Large Language Model)](https://aclanthology.org/2023.ccl-1.32) (Sun et al., CCL 2023)
ACL