@inproceedings{xiang-etal-2020-ji,
title = "基于{BERTCA}的新闻实体与正文语义相关度计算模型(Semantic Relevance Computing Model of News Entity and Text based on {BERTCA})",
author = "Xiang, Junyi and
Hu, Huijun and
Mao, Ruibin and
Liu, Maofu",
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-1.28",
pages = "288--300",
abstract = "目前的搜索引擎仍然存在{``}重形式,轻语义{''}的问题,无法做到对搜索关键词和文本的深层次语义理解,因此语义检索成为当代搜索引擎中亟需解决的问题。为了提高搜索引擎的语义理解能力,提出一种语义相关度的计算方法。首先标注金融类新闻标题实体与新闻正文语义相关度语料1万条,然后建立新闻实体与正文语义相关度计算的BERTCA(Bidirectional Encoder Representation from Transformers Co-Attention)模型,通过使用BERT预训练模型,综合考虑细粒度的实体和粗粒度的正文的语义信息,然后经过协同注意力,实现实体与正文的语义匹配,不仅能计算出金融新闻实体与新闻正文之间的相关度,还能根据相关度阈值来判定相关度类别,实验表明该模型在1万条标注语料上准确率超过95{\%},优于目前主流模型,最后通过具体搜索示例展现该模型的优秀性能。",
language = "Chinese",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xiang-etal-2020-ji">
<titleInfo>
<title>基于BERTCA的新闻实体与正文语义相关度计算模型(Semantic Relevance Computing Model of News Entity and Text based on BERTCA)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Junyi</namePart>
<namePart type="family">Xiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huijun</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruibin</namePart>
<namePart type="family">Mao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maofu</namePart>
<namePart type="family">Liu</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>目前的搜索引擎仍然存在“重形式,轻语义”的问题,无法做到对搜索关键词和文本的深层次语义理解,因此语义检索成为当代搜索引擎中亟需解决的问题。为了提高搜索引擎的语义理解能力,提出一种语义相关度的计算方法。首先标注金融类新闻标题实体与新闻正文语义相关度语料1万条,然后建立新闻实体与正文语义相关度计算的BERTCA(Bidirectional Encoder Representation from Transformers Co-Attention)模型,通过使用BERT预训练模型,综合考虑细粒度的实体和粗粒度的正文的语义信息,然后经过协同注意力,实现实体与正文的语义匹配,不仅能计算出金融新闻实体与新闻正文之间的相关度,还能根据相关度阈值来判定相关度类别,实验表明该模型在1万条标注语料上准确率超过95%,优于目前主流模型,最后通过具体搜索示例展现该模型的优秀性能。</abstract>
<identifier type="citekey">xiang-etal-2020-ji</identifier>
<location>
<url>https://aclanthology.org/2020.ccl-1.28</url>
</location>
<part>
<date>2020-10</date>
<extent unit="page">
<start>288</start>
<end>300</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T 基于BERTCA的新闻实体与正文语义相关度计算模型(Semantic Relevance Computing Model of News Entity and Text based on BERTCA)
%A Xiang, Junyi
%A Hu, Huijun
%A Mao, Ruibin
%A Liu, Maofu
%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 xiang-etal-2020-ji
%X 目前的搜索引擎仍然存在“重形式,轻语义”的问题,无法做到对搜索关键词和文本的深层次语义理解,因此语义检索成为当代搜索引擎中亟需解决的问题。为了提高搜索引擎的语义理解能力,提出一种语义相关度的计算方法。首先标注金融类新闻标题实体与新闻正文语义相关度语料1万条,然后建立新闻实体与正文语义相关度计算的BERTCA(Bidirectional Encoder Representation from Transformers Co-Attention)模型,通过使用BERT预训练模型,综合考虑细粒度的实体和粗粒度的正文的语义信息,然后经过协同注意力,实现实体与正文的语义匹配,不仅能计算出金融新闻实体与新闻正文之间的相关度,还能根据相关度阈值来判定相关度类别,实验表明该模型在1万条标注语料上准确率超过95%,优于目前主流模型,最后通过具体搜索示例展现该模型的优秀性能。
%U https://aclanthology.org/2020.ccl-1.28
%P 288-300
Markdown (Informal)
[基于BERTCA的新闻实体与正文语义相关度计算模型(Semantic Relevance Computing Model of News Entity and Text based on BERTCA)](https://aclanthology.org/2020.ccl-1.28) (Xiang et al., CCL 2020)
ACL