@inproceedings{wu-etal-2020-short,
title = "Short Text Topic Modeling with Topic Distribution Quantization and Negative Sampling Decoder",
author = "Wu, Xiaobao and
Li, Chunping and
Zhu, Yan and
Miao, Yishu",
editor = "Webber, Bonnie and
Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.emnlp-main.138",
doi = "10.18653/v1/2020.emnlp-main.138",
pages = "1772--1782",
abstract = "Topic models have been prevailing for many years on discovering latent semantics while modeling long documents. However, for short texts they generally suffer from data sparsity because of extremely limited word co-occurrences; thus tend to yield repetitive or trivial topics with low quality. In this paper, to address this issue, we propose a novel neural topic model in the framework of autoencoding with a new topic distribution quantization approach generating peakier distributions that are more appropriate for modeling short texts. Besides the encoding, to tackle this issue in terms of decoding, we further propose a novel negative sampling decoder learning from negative samples to avoid yielding repetitive topics. We observe that our model can highly improve short text topic modeling performance. Through extensive experiments on real-world datasets, we demonstrate our model can outperform both strong traditional and neural baselines under extreme data sparsity scenes, producing high-quality topics.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wu-etal-2020-short">
<titleInfo>
<title>Short Text Topic Modeling with Topic Distribution Quantization and Negative Sampling Decoder</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xiaobao</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chunping</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yan</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yishu</namePart>
<namePart type="family">Miao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bonnie</namePart>
<namePart type="family">Webber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</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>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Topic models have been prevailing for many years on discovering latent semantics while modeling long documents. However, for short texts they generally suffer from data sparsity because of extremely limited word co-occurrences; thus tend to yield repetitive or trivial topics with low quality. In this paper, to address this issue, we propose a novel neural topic model in the framework of autoencoding with a new topic distribution quantization approach generating peakier distributions that are more appropriate for modeling short texts. Besides the encoding, to tackle this issue in terms of decoding, we further propose a novel negative sampling decoder learning from negative samples to avoid yielding repetitive topics. We observe that our model can highly improve short text topic modeling performance. Through extensive experiments on real-world datasets, we demonstrate our model can outperform both strong traditional and neural baselines under extreme data sparsity scenes, producing high-quality topics.</abstract>
<identifier type="citekey">wu-etal-2020-short</identifier>
<identifier type="doi">10.18653/v1/2020.emnlp-main.138</identifier>
<location>
<url>https://aclanthology.org/2020.emnlp-main.138</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>1772</start>
<end>1782</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Short Text Topic Modeling with Topic Distribution Quantization and Negative Sampling Decoder
%A Wu, Xiaobao
%A Li, Chunping
%A Zhu, Yan
%A Miao, Yishu
%Y Webber, Bonnie
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F wu-etal-2020-short
%X Topic models have been prevailing for many years on discovering latent semantics while modeling long documents. However, for short texts they generally suffer from data sparsity because of extremely limited word co-occurrences; thus tend to yield repetitive or trivial topics with low quality. In this paper, to address this issue, we propose a novel neural topic model in the framework of autoencoding with a new topic distribution quantization approach generating peakier distributions that are more appropriate for modeling short texts. Besides the encoding, to tackle this issue in terms of decoding, we further propose a novel negative sampling decoder learning from negative samples to avoid yielding repetitive topics. We observe that our model can highly improve short text topic modeling performance. Through extensive experiments on real-world datasets, we demonstrate our model can outperform both strong traditional and neural baselines under extreme data sparsity scenes, producing high-quality topics.
%R 10.18653/v1/2020.emnlp-main.138
%U https://aclanthology.org/2020.emnlp-main.138
%U https://doi.org/10.18653/v1/2020.emnlp-main.138
%P 1772-1782
Markdown (Informal)
[Short Text Topic Modeling with Topic Distribution Quantization and Negative Sampling Decoder](https://aclanthology.org/2020.emnlp-main.138) (Wu et al., EMNLP 2020)
ACL