@article{dieng-etal-2020-topic,
title = "Topic Modeling in Embedding Spaces",
author = "Dieng, Adji B. and
Ruiz, Francisco J. R. and
Blei, David M.",
editor = "Johnson, Mark and
Roark, Brian and
Nenkova, Ani",
journal = "Transactions of the Association for Computational Linguistics",
volume = "8",
year = "2020",
address = "Cambridge, MA",
publisher = "MIT Press",
url = "https://aclanthology.org/2020.tacl-1.29/",
doi = "10.1162/tacl_a_00325",
pages = "439--453",
abstract = "Topic modeling analyzes documents to learn meaningful patterns of words. However, existing topic models fail to learn interpretable topics when working with large and heavy-tailed vocabularies. To this end, we develop the embedded topic model (etm), a generative model of documents that marries traditional topic models with word embeddings. More specifically, the etm models each word with a categorical distribution whose natural parameter is the inner product between the word`s embedding and an embedding of its assigned topic. To fit the etm, we develop an efficient amortized variational inference algorithm. The etm discovers interpretable topics even with large vocabularies that include rare words and stop words. It outperforms existing document models, such as latent Dirichlet allocation, in terms of both topic quality and predictive performance."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dieng-etal-2020-topic">
<titleInfo>
<title>Topic Modeling in Embedding Spaces</title>
</titleInfo>
<name type="personal">
<namePart type="given">Adji</namePart>
<namePart type="given">B</namePart>
<namePart type="family">Dieng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francisco</namePart>
<namePart type="given">J</namePart>
<namePart type="given">R</namePart>
<namePart type="family">Ruiz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Blei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<genre authority="bibutilsgt">journal article</genre>
<relatedItem type="host">
<titleInfo>
<title>Transactions of the Association for Computational Linguistics</title>
</titleInfo>
<originInfo>
<issuance>continuing</issuance>
<publisher>MIT Press</publisher>
<place>
<placeTerm type="text">Cambridge, MA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">periodical</genre>
<genre authority="bibutilsgt">academic journal</genre>
</relatedItem>
<abstract>Topic modeling analyzes documents to learn meaningful patterns of words. However, existing topic models fail to learn interpretable topics when working with large and heavy-tailed vocabularies. To this end, we develop the embedded topic model (etm), a generative model of documents that marries traditional topic models with word embeddings. More specifically, the etm models each word with a categorical distribution whose natural parameter is the inner product between the word‘s embedding and an embedding of its assigned topic. To fit the etm, we develop an efficient amortized variational inference algorithm. The etm discovers interpretable topics even with large vocabularies that include rare words and stop words. It outperforms existing document models, such as latent Dirichlet allocation, in terms of both topic quality and predictive performance.</abstract>
<identifier type="citekey">dieng-etal-2020-topic</identifier>
<identifier type="doi">10.1162/tacl_a_00325</identifier>
<location>
<url>https://aclanthology.org/2020.tacl-1.29/</url>
</location>
<part>
<date>2020</date>
<detail type="volume"><number>8</number></detail>
<extent unit="page">
<start>439</start>
<end>453</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Journal Article
%T Topic Modeling in Embedding Spaces
%A Dieng, Adji B.
%A Ruiz, Francisco J. R.
%A Blei, David M.
%J Transactions of the Association for Computational Linguistics
%D 2020
%V 8
%I MIT Press
%C Cambridge, MA
%F dieng-etal-2020-topic
%X Topic modeling analyzes documents to learn meaningful patterns of words. However, existing topic models fail to learn interpretable topics when working with large and heavy-tailed vocabularies. To this end, we develop the embedded topic model (etm), a generative model of documents that marries traditional topic models with word embeddings. More specifically, the etm models each word with a categorical distribution whose natural parameter is the inner product between the word‘s embedding and an embedding of its assigned topic. To fit the etm, we develop an efficient amortized variational inference algorithm. The etm discovers interpretable topics even with large vocabularies that include rare words and stop words. It outperforms existing document models, such as latent Dirichlet allocation, in terms of both topic quality and predictive performance.
%R 10.1162/tacl_a_00325
%U https://aclanthology.org/2020.tacl-1.29/
%U https://doi.org/10.1162/tacl_a_00325
%P 439-453
Markdown (Informal)
[Topic Modeling in Embedding Spaces](https://aclanthology.org/2020.tacl-1.29/) (Dieng et al., TACL 2020)
ACL
- Adji B. Dieng, Francisco J. R. Ruiz, and David M. Blei. 2020. Topic Modeling in Embedding Spaces. Transactions of the Association for Computational Linguistics, 8:439–453.