@inproceedings{qin-etal-2020-ji,
title = "基于多头注意力和{B}i{LSTM}改进{DAM}模型的中文问答匹配方法({C}hinese question answering method based on multi-head attention and {B}i{LSTM} improved {DAM} model)",
author = "Qin, Hanzhong and
Yu, Chongchong and
Jiang, Weijie and
Zhao, Xia",
editor = "Sun, Maosong and
Li, Sujian and
Zhang, Yue and
Liu, Yang",
booktitle = "Proceedings of the 19th Chinese National Conference on Computational Linguistics",
month = oct,
year = "2020",
address = "Haikou, China",
publisher = "Chinese Information Processing Society of China",
url = "https://aclanthology.org/2020.ccl-1.30",
pages = "313--323",
abstract = "针对目前检索式多轮对话深度注意力机制模型DAM(Deep Attention Matching Network)候选回复细节不匹配和语义混淆的问题,本文提出基于多头注意力和双向长短时记忆网络(BiLSTM)改进DAM模型的中文问答匹配方法,该方法采用多头注意力机制,使模型有能力建模较长的多轮对话,更好的处理目标回复与上下文的匹配关系。此外,本文在特征融合过程中采用BiLSTM模型,通过捕获多轮对话中的序列依赖关系,进一步提升选择目标候选回复的准确率。本文在豆瓣和电商两个开放数据集上进行实验,实验性能均优于DAM基线模型,R10@1指标在含有词向量增强的情况下提升了1.5{\%}。",
language = "Chinese",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="qin-etal-2020-ji">
<titleInfo>
<title>基于多头注意力和BiLSTM改进DAM模型的中文问答匹配方法(Chinese question answering method based on multi-head attention and BiLSTM improved DAM model)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hanzhong</namePart>
<namePart type="family">Qin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chongchong</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weijie</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xia</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-10</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 19th 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">Sujian</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</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>
<originInfo>
<publisher>Chinese Information Processing Society of China</publisher>
<place>
<placeTerm type="text">Haikou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>针对目前检索式多轮对话深度注意力机制模型DAM(Deep Attention Matching Network)候选回复细节不匹配和语义混淆的问题,本文提出基于多头注意力和双向长短时记忆网络(BiLSTM)改进DAM模型的中文问答匹配方法,该方法采用多头注意力机制,使模型有能力建模较长的多轮对话,更好的处理目标回复与上下文的匹配关系。此外,本文在特征融合过程中采用BiLSTM模型,通过捕获多轮对话中的序列依赖关系,进一步提升选择目标候选回复的准确率。本文在豆瓣和电商两个开放数据集上进行实验,实验性能均优于DAM基线模型,R10@1指标在含有词向量增强的情况下提升了1.5%。</abstract>
<identifier type="citekey">qin-etal-2020-ji</identifier>
<location>
<url>https://aclanthology.org/2020.ccl-1.30</url>
</location>
<part>
<date>2020-10</date>
<extent unit="page">
<start>313</start>
<end>323</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T 基于多头注意力和BiLSTM改进DAM模型的中文问答匹配方法(Chinese question answering method based on multi-head attention and BiLSTM improved DAM model)
%A Qin, Hanzhong
%A Yu, Chongchong
%A Jiang, Weijie
%A Zhao, Xia
%Y Sun, Maosong
%Y Li, Sujian
%Y Zhang, Yue
%Y Liu, Yang
%S Proceedings of the 19th Chinese National Conference on Computational Linguistics
%D 2020
%8 October
%I Chinese Information Processing Society of China
%C Haikou, China
%G Chinese
%F qin-etal-2020-ji
%X 针对目前检索式多轮对话深度注意力机制模型DAM(Deep Attention Matching Network)候选回复细节不匹配和语义混淆的问题,本文提出基于多头注意力和双向长短时记忆网络(BiLSTM)改进DAM模型的中文问答匹配方法,该方法采用多头注意力机制,使模型有能力建模较长的多轮对话,更好的处理目标回复与上下文的匹配关系。此外,本文在特征融合过程中采用BiLSTM模型,通过捕获多轮对话中的序列依赖关系,进一步提升选择目标候选回复的准确率。本文在豆瓣和电商两个开放数据集上进行实验,实验性能均优于DAM基线模型,R10@1指标在含有词向量增强的情况下提升了1.5%。
%U https://aclanthology.org/2020.ccl-1.30
%P 313-323
Markdown (Informal)
[基于多头注意力和BiLSTM改进DAM模型的中文问答匹配方法(Chinese question answering method based on multi-head attention and BiLSTM improved DAM model)](https://aclanthology.org/2020.ccl-1.30) (Qin et al., CCL 2020)
ACL