@inproceedings{yuru-etal-2024-ji,
title = "基于逻辑推理和多任务融合的认知刺激对话生成方法(Cognitive stimulation dialogue generation method based on logical reasoning and multi-task integration)",
author = "Yuru, Jiang and
Mengyuan, Li and
Yuyang, Tao and
Keming, Qu and
Zepeng, She and
Shuicai, Shi",
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-1.8/",
pages = "98--109",
language = "zho",
abstract = "{\textquotedblleft}在全球老龄化背景下,带有认知刺激的对话系统是保持老年人认知健康的重要手段。中文认知刺激对话数据集(Chinese Cognitive Stimulation Conversation Dataset,CSConv)和模型构建的研究工作刚刚开始。本文将认知刺激对话生成视为一个多任务融合的逻辑思维推理过程,将情感分类任务、决策任务和对话回复生成任务间的逻辑关系,建模为一个推理过程,来引导大语言模型生成。针对决策任务,本文提出分层编码器结构的决策模型。决策实验结果表明,决策模型有效的提高了决策任务的准确率。针对多任务过程,本文提出多任务融合方法,将三个任务对应的模型结合在一起。生成实验结果表明,分类、决策及生成的多任务融合方法,显著提升了对话回复能力,证明了该方法的有效性和先进性。{\textquotedblright}"
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yuru-etal-2024-ji">
<titleInfo>
<title>基于逻辑推理和多任务融合的认知刺激对话生成方法(Cognitive stimulation dialogue generation method based on logical reasoning and multi-task integration)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jiang</namePart>
<namePart type="family">Yuru</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Li</namePart>
<namePart type="family">Mengyuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tao</namePart>
<namePart type="family">Yuyang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qu</namePart>
<namePart type="family">Keming</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">She</namePart>
<namePart type="family">Zepeng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shi</namePart>
<namePart type="family">Shuicai</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>“在全球老龄化背景下,带有认知刺激的对话系统是保持老年人认知健康的重要手段。中文认知刺激对话数据集(Chinese Cognitive Stimulation Conversation Dataset,CSConv)和模型构建的研究工作刚刚开始。本文将认知刺激对话生成视为一个多任务融合的逻辑思维推理过程,将情感分类任务、决策任务和对话回复生成任务间的逻辑关系,建模为一个推理过程,来引导大语言模型生成。针对决策任务,本文提出分层编码器结构的决策模型。决策实验结果表明,决策模型有效的提高了决策任务的准确率。针对多任务过程,本文提出多任务融合方法,将三个任务对应的模型结合在一起。生成实验结果表明,分类、决策及生成的多任务融合方法,显著提升了对话回复能力,证明了该方法的有效性和先进性。”</abstract>
<identifier type="citekey">yuru-etal-2024-ji</identifier>
<location>
<url>https://aclanthology.org/2024.ccl-1.8/</url>
</location>
<part>
<date>2024-07</date>
<extent unit="page">
<start>98</start>
<end>109</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T 基于逻辑推理和多任务融合的认知刺激对话生成方法(Cognitive stimulation dialogue generation method based on logical reasoning and multi-task integration)
%A Yuru, Jiang
%A Mengyuan, Li
%A Yuyang, Tao
%A Keming, Qu
%A Zepeng, She
%A Shuicai, Shi
%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 yuru-etal-2024-ji
%X “在全球老龄化背景下,带有认知刺激的对话系统是保持老年人认知健康的重要手段。中文认知刺激对话数据集(Chinese Cognitive Stimulation Conversation Dataset,CSConv)和模型构建的研究工作刚刚开始。本文将认知刺激对话生成视为一个多任务融合的逻辑思维推理过程,将情感分类任务、决策任务和对话回复生成任务间的逻辑关系,建模为一个推理过程,来引导大语言模型生成。针对决策任务,本文提出分层编码器结构的决策模型。决策实验结果表明,决策模型有效的提高了决策任务的准确率。针对多任务过程,本文提出多任务融合方法,将三个任务对应的模型结合在一起。生成实验结果表明,分类、决策及生成的多任务融合方法,显著提升了对话回复能力,证明了该方法的有效性和先进性。”
%U https://aclanthology.org/2024.ccl-1.8/
%P 98-109
Markdown (Informal)
[基于逻辑推理和多任务融合的认知刺激对话生成方法(Cognitive stimulation dialogue generation method based on logical reasoning and multi-task integration)](https://aclanthology.org/2024.ccl-1.8/) (Yuru et al., CCL 2024)
ACL