@inproceedings{wood-etal-2022-bayesian,
title = "A {B}ayesian Topic Model for Human-Evaluated Interpretability",
author = "Wood, Justin and
Arnold, Corey and
Wang, Wei",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.674/",
pages = "6271--6279",
abstract = "One desiderata of topic modeling is to produce interpretable topics. Given a cluster of document-tokens comprising a topic, we can order the topic by counting each word. It is natural to think that each topic could easily be labeled by looking at the words with the highest word count. However, this is not always the case. A human evaluator can often have difficulty identifying a single label that accurately describes the topic as many top words seem unrelated. This paper aims to improve interpretability in topic modeling by providing a novel, outperforming interpretable topic model Our approach combines two previously established subdomains in topic modeling: nonparametric and weakly-supervised topic models. Given a nonparametric topic model, we can include weakly-supervised input using novel modifications to the nonparametric generative model. These modifications lay the groundwork for a compelling setting{---}one in which most corpora, without any previous supervised or weakly-supervised input, can discover interpretable topics. This setting also presents various challenging sub-problems of which we provide resolutions. Combining nonparametric topic models with weakly-supervised topic models leads to an exciting discovery{---}a complete, self-contained and outperforming topic model for interpretability."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wood-etal-2022-bayesian">
<titleInfo>
<title>A Bayesian Topic Model for Human-Evaluated Interpretability</title>
</titleInfo>
<name type="personal">
<namePart type="given">Justin</namePart>
<namePart type="family">Wood</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Corey</namePart>
<namePart type="family">Arnold</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>One desiderata of topic modeling is to produce interpretable topics. Given a cluster of document-tokens comprising a topic, we can order the topic by counting each word. It is natural to think that each topic could easily be labeled by looking at the words with the highest word count. However, this is not always the case. A human evaluator can often have difficulty identifying a single label that accurately describes the topic as many top words seem unrelated. This paper aims to improve interpretability in topic modeling by providing a novel, outperforming interpretable topic model Our approach combines two previously established subdomains in topic modeling: nonparametric and weakly-supervised topic models. Given a nonparametric topic model, we can include weakly-supervised input using novel modifications to the nonparametric generative model. These modifications lay the groundwork for a compelling setting—one in which most corpora, without any previous supervised or weakly-supervised input, can discover interpretable topics. This setting also presents various challenging sub-problems of which we provide resolutions. Combining nonparametric topic models with weakly-supervised topic models leads to an exciting discovery—a complete, self-contained and outperforming topic model for interpretability.</abstract>
<identifier type="citekey">wood-etal-2022-bayesian</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.674/</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>6271</start>
<end>6279</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Bayesian Topic Model for Human-Evaluated Interpretability
%A Wood, Justin
%A Arnold, Corey
%A Wang, Wei
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F wood-etal-2022-bayesian
%X One desiderata of topic modeling is to produce interpretable topics. Given a cluster of document-tokens comprising a topic, we can order the topic by counting each word. It is natural to think that each topic could easily be labeled by looking at the words with the highest word count. However, this is not always the case. A human evaluator can often have difficulty identifying a single label that accurately describes the topic as many top words seem unrelated. This paper aims to improve interpretability in topic modeling by providing a novel, outperforming interpretable topic model Our approach combines two previously established subdomains in topic modeling: nonparametric and weakly-supervised topic models. Given a nonparametric topic model, we can include weakly-supervised input using novel modifications to the nonparametric generative model. These modifications lay the groundwork for a compelling setting—one in which most corpora, without any previous supervised or weakly-supervised input, can discover interpretable topics. This setting also presents various challenging sub-problems of which we provide resolutions. Combining nonparametric topic models with weakly-supervised topic models leads to an exciting discovery—a complete, self-contained and outperforming topic model for interpretability.
%U https://aclanthology.org/2022.lrec-1.674/
%P 6271-6279
Markdown (Informal)
[A Bayesian Topic Model for Human-Evaluated Interpretability](https://aclanthology.org/2022.lrec-1.674/) (Wood et al., LREC 2022)
ACL