@inproceedings{liang-etal-2021-ji,
title = "基于堆叠式注意力网络的复杂话语领域分类方法(Complex Utterance Domain Classification Using Stacked Attention Networks)",
author = "Liang, Chaojie and
Huang, Peijie and
Ding, Jiande and
Zhu, Jiankai and
Lin, Piyuan",
editor = "Li, Sheng and
Sun, Maosong and
Liu, Yang and
Wu, Hua and
Liu, Kang and
Che, Wanxiang and
He, Shizhu and
Rao, Gaoqi",
booktitle = "Proceedings of the 20th Chinese National Conference on Computational Linguistics",
month = aug,
year = "2021",
address = "Huhhot, China",
publisher = "Chinese Information Processing Society of China",
url = "https://aclanthology.org/2021.ccl-1.69",
pages = "769--780",
abstract = "话语领域分类(utterance domain classification UDC)是口语语言理解(spoken lan-guage understanding SLU)中语义分析的关键步骤。尽管带注意力机制的递归神经网络已经得到了广泛的应用,并将UDC的研究进展提高到了一个新的水平,但是对于复杂的话语,如长度较长的话语或带有逗号的复合句的话语,有效的UDC仍然是一个挑战。本文提出一种基于堆叠式注意力网络的话语领域分类方法SAN-DC(stacked attention networks-DC)。该模型综合了对口语话语多层次的语言特征的捕捉,增强对复杂话语的理解。首先在模型底层采用语境化词向量(contextualized word embedding)得到良好的词汇特征表达,并在词法层采用长短期记忆网络(long short-term memory)将话语编码为上下文向量表示。接着在语法级别上使用自注意力机制(self-attention mechanism)来捕捉特定领域的词依赖,然后使用词注意力(word-attention)层提取语义信息。最后使用残差连接(residual connection)将低层语言信息传递到高层,更好地实现多层语言信息的融合。本文在中文话语领域分类基准语料SMP-ECDT上验证所提出的方法的有效性。通过与研究进展的文本分类模型对比,本文的方法取得了较高的话语领域分类正确率。尤其是对于较为复杂的用户话语,本文提出的方法较研究进展方法的性能提升更为显著。",
language = "Chinese",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liang-etal-2021-ji">
<titleInfo>
<title>基于堆叠式注意力网络的复杂话语领域分类方法(Complex Utterance Domain Classification Using Stacked Attention Networks)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chaojie</namePart>
<namePart type="family">Liang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peijie</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiande</namePart>
<namePart type="family">Ding</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiankai</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Piyuan</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</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 20th Chinese National Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sheng</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hua</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shizhu</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gaoqi</namePart>
<namePart type="family">Rao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Chinese Information Processing Society of China</publisher>
<place>
<placeTerm type="text">Huhhot, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>话语领域分类(utterance domain classification UDC)是口语语言理解(spoken lan-guage understanding SLU)中语义分析的关键步骤。尽管带注意力机制的递归神经网络已经得到了广泛的应用,并将UDC的研究进展提高到了一个新的水平,但是对于复杂的话语,如长度较长的话语或带有逗号的复合句的话语,有效的UDC仍然是一个挑战。本文提出一种基于堆叠式注意力网络的话语领域分类方法SAN-DC(stacked attention networks-DC)。该模型综合了对口语话语多层次的语言特征的捕捉,增强对复杂话语的理解。首先在模型底层采用语境化词向量(contextualized word embedding)得到良好的词汇特征表达,并在词法层采用长短期记忆网络(long short-term memory)将话语编码为上下文向量表示。接着在语法级别上使用自注意力机制(self-attention mechanism)来捕捉特定领域的词依赖,然后使用词注意力(word-attention)层提取语义信息。最后使用残差连接(residual connection)将低层语言信息传递到高层,更好地实现多层语言信息的融合。本文在中文话语领域分类基准语料SMP-ECDT上验证所提出的方法的有效性。通过与研究进展的文本分类模型对比,本文的方法取得了较高的话语领域分类正确率。尤其是对于较为复杂的用户话语,本文提出的方法较研究进展方法的性能提升更为显著。</abstract>
<identifier type="citekey">liang-etal-2021-ji</identifier>
<location>
<url>https://aclanthology.org/2021.ccl-1.69</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>769</start>
<end>780</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T 基于堆叠式注意力网络的复杂话语领域分类方法(Complex Utterance Domain Classification Using Stacked Attention Networks)
%A Liang, Chaojie
%A Huang, Peijie
%A Ding, Jiande
%A Zhu, Jiankai
%A Lin, Piyuan
%Y Li, Sheng
%Y Sun, Maosong
%Y Liu, Yang
%Y Wu, Hua
%Y Liu, Kang
%Y Che, Wanxiang
%Y He, Shizhu
%Y Rao, Gaoqi
%S Proceedings of the 20th Chinese National Conference on Computational Linguistics
%D 2021
%8 August
%I Chinese Information Processing Society of China
%C Huhhot, China
%G Chinese
%F liang-etal-2021-ji
%X 话语领域分类(utterance domain classification UDC)是口语语言理解(spoken lan-guage understanding SLU)中语义分析的关键步骤。尽管带注意力机制的递归神经网络已经得到了广泛的应用,并将UDC的研究进展提高到了一个新的水平,但是对于复杂的话语,如长度较长的话语或带有逗号的复合句的话语,有效的UDC仍然是一个挑战。本文提出一种基于堆叠式注意力网络的话语领域分类方法SAN-DC(stacked attention networks-DC)。该模型综合了对口语话语多层次的语言特征的捕捉,增强对复杂话语的理解。首先在模型底层采用语境化词向量(contextualized word embedding)得到良好的词汇特征表达,并在词法层采用长短期记忆网络(long short-term memory)将话语编码为上下文向量表示。接着在语法级别上使用自注意力机制(self-attention mechanism)来捕捉特定领域的词依赖,然后使用词注意力(word-attention)层提取语义信息。最后使用残差连接(residual connection)将低层语言信息传递到高层,更好地实现多层语言信息的融合。本文在中文话语领域分类基准语料SMP-ECDT上验证所提出的方法的有效性。通过与研究进展的文本分类模型对比,本文的方法取得了较高的话语领域分类正确率。尤其是对于较为复杂的用户话语,本文提出的方法较研究进展方法的性能提升更为显著。
%U https://aclanthology.org/2021.ccl-1.69
%P 769-780
Markdown (Informal)
[基于堆叠式注意力网络的复杂话语领域分类方法(Complex Utterance Domain Classification Using Stacked Attention Networks)](https://aclanthology.org/2021.ccl-1.69) (Liang et al., CCL 2021)
ACL