@inproceedings{byrne-etal-2022-topic,
title = "Topic Modeling With Topological Data Analysis",
author = "Byrne, Ciar{\'a}n and
Horak, Danijela and
Moilanen, Karo and
Mabona, Amandla",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.emnlp-main.792",
doi = "10.18653/v1/2022.emnlp-main.792",
pages = "11514--11533",
abstract = "Recent unsupervised topic modelling ap-proaches that use clustering techniques onword, token or document embeddings can ex-tract coherent topics. A common limitationof such approaches is that they reveal noth-ing about inter-topic relationships which areessential in many real-world application do-mains. We present an unsupervised topic mod-elling method which harnesses TopologicalData Analysis (TDA) to extract a topologicalskeleton of the manifold upon which contextu-alised word embeddings lie. We demonstratethat our approach, which performs on par witha recent baseline, is able to construct a networkof coherent topics together with meaningfulrelationships between them.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="byrne-etal-2022-topic">
<titleInfo>
<title>Topic Modeling With Topological Data Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ciarán</namePart>
<namePart type="family">Byrne</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Danijela</namePart>
<namePart type="family">Horak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karo</namePart>
<namePart type="family">Moilanen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amandla</namePart>
<namePart type="family">Mabona</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recent unsupervised topic modelling ap-proaches that use clustering techniques onword, token or document embeddings can ex-tract coherent topics. A common limitationof such approaches is that they reveal noth-ing about inter-topic relationships which areessential in many real-world application do-mains. We present an unsupervised topic mod-elling method which harnesses TopologicalData Analysis (TDA) to extract a topologicalskeleton of the manifold upon which contextu-alised word embeddings lie. We demonstratethat our approach, which performs on par witha recent baseline, is able to construct a networkof coherent topics together with meaningfulrelationships between them.</abstract>
<identifier type="citekey">byrne-etal-2022-topic</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-main.792</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-main.792</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>11514</start>
<end>11533</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Topic Modeling With Topological Data Analysis
%A Byrne, Ciarán
%A Horak, Danijela
%A Moilanen, Karo
%A Mabona, Amandla
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F byrne-etal-2022-topic
%X Recent unsupervised topic modelling ap-proaches that use clustering techniques onword, token or document embeddings can ex-tract coherent topics. A common limitationof such approaches is that they reveal noth-ing about inter-topic relationships which areessential in many real-world application do-mains. We present an unsupervised topic mod-elling method which harnesses TopologicalData Analysis (TDA) to extract a topologicalskeleton of the manifold upon which contextu-alised word embeddings lie. We demonstratethat our approach, which performs on par witha recent baseline, is able to construct a networkof coherent topics together with meaningfulrelationships between them.
%R 10.18653/v1/2022.emnlp-main.792
%U https://aclanthology.org/2022.emnlp-main.792
%U https://doi.org/10.18653/v1/2022.emnlp-main.792
%P 11514-11533
Markdown (Informal)
[Topic Modeling With Topological Data Analysis](https://aclanthology.org/2022.emnlp-main.792) (Byrne et al., EMNLP 2022)
ACL
- Ciarán Byrne, Danijela Horak, Karo Moilanen, and Amandla Mabona. 2022. Topic Modeling With Topological Data Analysis. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 11514–11533, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.