<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cao-etal-2022-sheng">
    <titleInfo>
        <title>生成,推理与排序:基于多任务架构的数学文字题生成(Generating, Reasoning &amp; Ranking: Multitask Learning Framework for Math Word Problem Generation)</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Tianyang</namePart>
        <namePart type="family">Cao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xiaodan</namePart>
        <namePart type="family">Xu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Baobao</namePart>
        <namePart type="family">Chang</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>
        <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>“数学文字题是一段能反映数学等式潜在逻辑的叙述性文本。成功的数学问题生成在语言生成和教育领域都具有广阔的应用前景。前人的工作大多需要人工标注的模板或关键词作为输入,且未考虑数学表达式本身的特点。本文提出了一种多任务联合训练的问题文本生成模型。我们设计了三个辅助任务,包括数字间关系抽取、数值排序和片段替换预测。他们与生成目标联合训练,用以监督解码器的学习,增强模型对运算逻辑和问题条件的感知能力。实验证明所提方法能有效提升生成的数学文字题的质量。”</abstract>
    <identifier type="citekey">cao-etal-2022-sheng</identifier>
    <location>
        <url>https://aclanthology.org/2022.ccl-1.17</url>
    </location>
    <part>
        <date>2022-10</date>
        <extent unit="page">
            <start>178</start>
            <end>189</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T 生成,推理与排序:基于多任务架构的数学文字题生成(Generating, Reasoning & Ranking: Multitask Learning Framework for Math Word Problem Generation)
%A Cao, Tianyang
%A Xu, Xiaodan
%A Chang, Baobao
%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 cao-etal-2022-sheng
%X “数学文字题是一段能反映数学等式潜在逻辑的叙述性文本。成功的数学问题生成在语言生成和教育领域都具有广阔的应用前景。前人的工作大多需要人工标注的模板或关键词作为输入,且未考虑数学表达式本身的特点。本文提出了一种多任务联合训练的问题文本生成模型。我们设计了三个辅助任务,包括数字间关系抽取、数值排序和片段替换预测。他们与生成目标联合训练,用以监督解码器的学习,增强模型对运算逻辑和问题条件的感知能力。实验证明所提方法能有效提升生成的数学文字题的质量。”
%U https://aclanthology.org/2022.ccl-1.17
%P 178-189

Markdown (Informal)

[生成,推理与排序:基于多任务架构的数学文字题生成(Generating, Reasoning & Ranking: Multitask Learning Framework for Math Word Problem Generation)](https://aclanthology.org/2022.ccl-1.17) (Cao et al., CCL 2022)

• 生成,推理与排序:基于多任务架构的数学文字题生成(Generating, Reasoning & Ranking: Multitask Learning Framework for Math Word Problem Generation) (Cao et al., CCL 2022)

ACL

• Tianyang Cao, Xiaodan Xu, and Baobao Chang. 2022. 生成,推理与排序:基于多任务架构的数学文字题生成(Generating, Reasoning & Ranking: Multitask Learning Framework for Math Word Problem Generation). In Proceedings of the 21st Chinese National Conference on Computational Linguistics, pages 178–189, Nanchang, China. Chinese Information Processing Society of China.