@inproceedings{guo-etal-2020-ji,
title = "基于半监督学习的中文社交文本事件聚类方法(Semi-supervised Method to Cluster {C}hinese Events on Social Streams)",
author = "Guo, Hengrui and
Wang, Zhongqing and
Li, Peifeng and
Zhu, Qiaoming",
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-1.59/",
pages = "634--644",
language = "zho",
abstract = "面向社交媒体的事件聚类旨在根据事件特征对短文本聚类。目前,事件聚类模型主要分为无监督模型和有监督模型。无监督模型聚类效果较差,有监督模型依赖大量标注数据。基于此,本文提出了一种半监督事件聚类模型(SemiEC),该模型在小规模标注数据的基础上,利用LSTM表征事件,利用线性模型计算文本相似度,进行增量聚类,利用增量聚类产生的标注数据对模型再训练,结束后对不确定样本再聚类。实验表明,SemiEC的性能相比其他模型均有所提高。"
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="guo-etal-2020-ji">
<titleInfo>
<title>基于半监督学习的中文社交文本事件聚类方法(Semi-supervised Method to Cluster Chinese Events on Social Streams)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hengrui</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhongqing</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peifeng</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qiaoming</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">zho</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>面向社交媒体的事件聚类旨在根据事件特征对短文本聚类。目前,事件聚类模型主要分为无监督模型和有监督模型。无监督模型聚类效果较差,有监督模型依赖大量标注数据。基于此,本文提出了一种半监督事件聚类模型(SemiEC),该模型在小规模标注数据的基础上,利用LSTM表征事件,利用线性模型计算文本相似度,进行增量聚类,利用增量聚类产生的标注数据对模型再训练,结束后对不确定样本再聚类。实验表明,SemiEC的性能相比其他模型均有所提高。</abstract>
<identifier type="citekey">guo-etal-2020-ji</identifier>
<location>
<url>https://aclanthology.org/2020.ccl-1.59/</url>
</location>
<part>
<date>2020-10</date>
<extent unit="page">
<start>634</start>
<end>644</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T 基于半监督学习的中文社交文本事件聚类方法(Semi-supervised Method to Cluster Chinese Events on Social Streams)
%A Guo, Hengrui
%A Wang, Zhongqing
%A Li, Peifeng
%A Zhu, Qiaoming
%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 zho
%F guo-etal-2020-ji
%X 面向社交媒体的事件聚类旨在根据事件特征对短文本聚类。目前,事件聚类模型主要分为无监督模型和有监督模型。无监督模型聚类效果较差,有监督模型依赖大量标注数据。基于此,本文提出了一种半监督事件聚类模型(SemiEC),该模型在小规模标注数据的基础上,利用LSTM表征事件,利用线性模型计算文本相似度,进行增量聚类,利用增量聚类产生的标注数据对模型再训练,结束后对不确定样本再聚类。实验表明,SemiEC的性能相比其他模型均有所提高。
%U https://aclanthology.org/2020.ccl-1.59/
%P 634-644
Markdown (Informal)
[基于半监督学习的中文社交文本事件聚类方法(Semi-supervised Method to Cluster Chinese Events on Social Streams)](https://aclanthology.org/2020.ccl-1.59/) (Guo et al., CCL 2020)
ACL