@inproceedings{venkatesaramani-etal-2019-semantic,
title = "A Semantic Cover Approach for Topic Modeling",
author = "Venkatesaramani, Rajagopal and
Downey, Doug and
Malin, Bradley and
Vorobeychik, Yevgeniy",
editor = "Mihalcea, Rada and
Shutova, Ekaterina and
Ku, Lun-Wei and
Evang, Kilian and
Poria, Soujanya",
booktitle = "Proceedings of the Eighth Joint Conference on Lexical and Computational Semantics (*{SEM} 2019)",
month = jun,
year = "2019",
address = "Minneapolis, Minnesota",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/S19-1011",
doi = "10.18653/v1/S19-1011",
pages = "92--102",
abstract = "We introduce a novel topic modeling approach based on constructing a semantic set cover for clusters of similar documents. Specifically, our approach first clusters documents using their Tf-Idf representation, and then covers each cluster with a set of topic words based on semantic similarity, defined in terms of a word embedding. Computing a topic cover amounts to solving a minimum set cover problem. Our evaluation compares our topic modeling approach to Latent Dirichlet Allocation (LDA) on three metrics: 1) qualitative topic match, measured using evaluations by Amazon Mechanical Turk (MTurk) workers, 2) performance on classification tasks using each topic model as a sparse feature representation, and 3) topic coherence. We find that qualitative judgments significantly favor our approach, the method outperforms LDA on topic coherence, and is comparable to LDA on document classification tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="venkatesaramani-etal-2019-semantic">
<titleInfo>
<title>A Semantic Cover Approach for Topic Modeling</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rajagopal</namePart>
<namePart type="family">Venkatesaramani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Doug</namePart>
<namePart type="family">Downey</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bradley</namePart>
<namePart type="family">Malin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yevgeniy</namePart>
<namePart type="family">Vorobeychik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth Joint Conference on Lexical and Computational Semantics (*SEM 2019)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rada</namePart>
<namePart type="family">Mihalcea</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kilian</namePart>
<namePart type="family">Evang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Soujanya</namePart>
<namePart type="family">Poria</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Minneapolis, Minnesota</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We introduce a novel topic modeling approach based on constructing a semantic set cover for clusters of similar documents. Specifically, our approach first clusters documents using their Tf-Idf representation, and then covers each cluster with a set of topic words based on semantic similarity, defined in terms of a word embedding. Computing a topic cover amounts to solving a minimum set cover problem. Our evaluation compares our topic modeling approach to Latent Dirichlet Allocation (LDA) on three metrics: 1) qualitative topic match, measured using evaluations by Amazon Mechanical Turk (MTurk) workers, 2) performance on classification tasks using each topic model as a sparse feature representation, and 3) topic coherence. We find that qualitative judgments significantly favor our approach, the method outperforms LDA on topic coherence, and is comparable to LDA on document classification tasks.</abstract>
<identifier type="citekey">venkatesaramani-etal-2019-semantic</identifier>
<identifier type="doi">10.18653/v1/S19-1011</identifier>
<location>
<url>https://aclanthology.org/S19-1011</url>
</location>
<part>
<date>2019-06</date>
<extent unit="page">
<start>92</start>
<end>102</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Semantic Cover Approach for Topic Modeling
%A Venkatesaramani, Rajagopal
%A Downey, Doug
%A Malin, Bradley
%A Vorobeychik, Yevgeniy
%Y Mihalcea, Rada
%Y Shutova, Ekaterina
%Y Ku, Lun-Wei
%Y Evang, Kilian
%Y Poria, Soujanya
%S Proceedings of the Eighth Joint Conference on Lexical and Computational Semantics (*SEM 2019)
%D 2019
%8 June
%I Association for Computational Linguistics
%C Minneapolis, Minnesota
%F venkatesaramani-etal-2019-semantic
%X We introduce a novel topic modeling approach based on constructing a semantic set cover for clusters of similar documents. Specifically, our approach first clusters documents using their Tf-Idf representation, and then covers each cluster with a set of topic words based on semantic similarity, defined in terms of a word embedding. Computing a topic cover amounts to solving a minimum set cover problem. Our evaluation compares our topic modeling approach to Latent Dirichlet Allocation (LDA) on three metrics: 1) qualitative topic match, measured using evaluations by Amazon Mechanical Turk (MTurk) workers, 2) performance on classification tasks using each topic model as a sparse feature representation, and 3) topic coherence. We find that qualitative judgments significantly favor our approach, the method outperforms LDA on topic coherence, and is comparable to LDA on document classification tasks.
%R 10.18653/v1/S19-1011
%U https://aclanthology.org/S19-1011
%U https://doi.org/10.18653/v1/S19-1011
%P 92-102
Markdown (Informal)
[A Semantic Cover Approach for Topic Modeling](https://aclanthology.org/S19-1011) (Venkatesaramani et al., *SEM 2019)
ACL
- Rajagopal Venkatesaramani, Doug Downey, Bradley Malin, and Yevgeniy Vorobeychik. 2019. A Semantic Cover Approach for Topic Modeling. In Proceedings of the Eighth Joint Conference on Lexical and Computational Semantics (*SEM 2019), pages 92–102, Minneapolis, Minnesota. Association for Computational Linguistics.