@inproceedings{sia-etal-2020-tired,
title = "Tired of Topic Models? Clusters of Pretrained Word Embeddings Make for Fast and Good Topics too!",
author = "Sia, Suzanna and
Dalmia, Ayush and
Mielke, Sabrina J.",
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.135",
doi = "10.18653/v1/2020.emnlp-main.135",
pages = "1728--1736",
abstract = "Topic models are a useful analysis tool to uncover the underlying themes within document collections. The dominant approach is to use probabilistic topic models that posit a generative story, but in this paper we propose an alternative way to obtain topics: clustering pre-trained word embeddings while incorporating document information for weighted clustering and reranking top words. We provide benchmarks for the combination of different word embeddings and clustering algorithms, and analyse their performance under dimensionality reduction with PCA. The best performing combination for our approach performs as well as classical topic models, but with lower runtime and computational complexity.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sia-etal-2020-tired">
<titleInfo>
<title>Tired of Topic Models? Clusters of Pretrained Word Embeddings Make for Fast and Good Topics too!</title>
</titleInfo>
<name type="personal">
<namePart type="given">Suzanna</namePart>
<namePart type="family">Sia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayush</namePart>
<namePart type="family">Dalmia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sabrina</namePart>
<namePart type="given">J</namePart>
<namePart type="family">Mielke</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 are a useful analysis tool to uncover the underlying themes within document collections. The dominant approach is to use probabilistic topic models that posit a generative story, but in this paper we propose an alternative way to obtain topics: clustering pre-trained word embeddings while incorporating document information for weighted clustering and reranking top words. We provide benchmarks for the combination of different word embeddings and clustering algorithms, and analyse their performance under dimensionality reduction with PCA. The best performing combination for our approach performs as well as classical topic models, but with lower runtime and computational complexity.</abstract>
<identifier type="citekey">sia-etal-2020-tired</identifier>
<identifier type="doi">10.18653/v1/2020.emnlp-main.135</identifier>
<location>
<url>https://aclanthology.org/2020.emnlp-main.135</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>1728</start>
<end>1736</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Tired of Topic Models? Clusters of Pretrained Word Embeddings Make for Fast and Good Topics too!
%A Sia, Suzanna
%A Dalmia, Ayush
%A Mielke, Sabrina J.
%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 sia-etal-2020-tired
%X Topic models are a useful analysis tool to uncover the underlying themes within document collections. The dominant approach is to use probabilistic topic models that posit a generative story, but in this paper we propose an alternative way to obtain topics: clustering pre-trained word embeddings while incorporating document information for weighted clustering and reranking top words. We provide benchmarks for the combination of different word embeddings and clustering algorithms, and analyse their performance under dimensionality reduction with PCA. The best performing combination for our approach performs as well as classical topic models, but with lower runtime and computational complexity.
%R 10.18653/v1/2020.emnlp-main.135
%U https://aclanthology.org/2020.emnlp-main.135
%U https://doi.org/10.18653/v1/2020.emnlp-main.135
%P 1728-1736
Markdown (Informal)
[Tired of Topic Models? Clusters of Pretrained Word Embeddings Make for Fast and Good Topics too!](https://aclanthology.org/2020.emnlp-main.135) (Sia et al., EMNLP 2020)
ACL