Interpretable Topic Modeling Using Near-Identity Cross-Document Coreference Resolution

Zhukova, Anastasia; Hamborg, Felix; Gipp, Bela

Interpretable Topic Modeling Using Near-Identity Cross-Document Coreference Resolution

Files

There are no files associated with this item.

Date

2020

Publication type

Contribution to a conference collection

Publication status

Published

Published in

Proceedings of the ACM/IEEE Joint Conference on Digital Libraries in 2020 (JCDL '20) / Huang, Ruhua et al. (ed.). - New York : ACM, 2020. - pp. 461-462. - ISBN 978-1-4503-7585-6

Abstract

Topic modeling is a technique used in a broad spectrum of use cases, such as data exploration, summarization, and classification. Despite being a crucial constituent of many use cases, established topic models, such as LDA, often produce statistically valid yet non-meaningful topics, i.e., that cannot easily be interpreted by humans. In turn, the usability of topic modeling approaches, e.g., in document summarization, is non-optimal. We propose a topic modeling approach that uses TCA, a method for also near-identity cross-document coreference resolution. TCA showed promising results when resolving mentions of not only persons and other named entities, but also broad, vague, or abstract concepts. In a preliminary evaluation on news articles, we compare the approach with state-of-the-art topic modeling. We find that (1) the four baselines produce statistically valid yet hollow topics or topics that only refer to events in the dataset but not the events' topical composition. (2) TCA is the only approach that extracts topics that distinctively describe meaningful parts of the dataset.

Subject (DDC)

004 Computer Science

Conference

JCDL '20, Aug 1, 2020 - Aug 5, 2020, China (Virtual Event)

Cite This

ISO 690

ZHUKOVA, Anastasia, Felix HAMBORG, Bela GIPP, 2020. Interpretable Topic Modeling Using Near-Identity Cross-Document Coreference Resolution. JCDL '20. China (Virtual Event), Aug 1, 2020 - Aug 5, 2020. In: HUANG, Ruhua, ed. and others. Proceedings of the ACM/IEEE Joint Conference on Digital Libraries in 2020 (JCDL '20). New York:ACM, pp. 461-462. ISBN 978-1-4503-7585-6. Available under: doi: 10.1145/3383583.3398564

BibTex

@inproceedings{Zhukova2020Inter-51922,
  year={2020},
  doi={10.1145/3383583.3398564},
  title={Interpretable Topic Modeling Using Near-Identity Cross-Document Coreference Resolution},
  isbn={978-1-4503-7585-6},
  publisher={ACM},
  address={New York},
  booktitle={Proceedings of the ACM/IEEE Joint Conference on Digital Libraries in 2020 (JCDL '20)},
  pages={461--462},
  editor={Huang, Ruhua},
  author={Zhukova, Anastasia and Hamborg, Felix and Gipp, Bela}
}

RDF

<rdf:RDF
    xmlns:dcterms="http://purl.org/dc/terms/"
    xmlns:dc="http://purl.org/dc/elements/1.1/"
    xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
    xmlns:bibo="http://purl.org/ontology/bibo/"
    xmlns:dspace="http://digital-repositories.org/ontologies/dspace/0.1.0#"
    xmlns:foaf="http://xmlns.com/foaf/0.1/"
    xmlns:void="http://rdfs.org/ns/void#"
    xmlns:xsd="http://www.w3.org/2001/XMLSchema#" > 
  <rdf:Description rdf:about="https://kops.uni-konstanz.de/server/rdf/resource/123456789/51922">
    <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2020-11-25T14:22:35Z</dc:date>
    <dc:rights>terms-of-use</dc:rights>
    <dcterms:abstract xml:lang="eng">Topic modeling is a technique used in a broad spectrum of use cases, such as data exploration, summarization, and classification. Despite being a crucial constituent of many use cases, established topic models, such as LDA, often produce statistically valid yet non-meaningful topics, i.e., that cannot easily be interpreted by humans. In turn, the usability of topic modeling approaches, e.g., in document summarization, is non-optimal. We propose a topic modeling approach that uses TCA, a method for also near-identity cross-document coreference resolution. TCA showed promising results when resolving mentions of not only persons and other named entities, but also broad, vague, or abstract concepts. In a preliminary evaluation on news articles, we compare the approach with state-of-the-art topic modeling. We find that (1) the four baselines produce statistically valid yet hollow topics or topics that only refer to events in the dataset but not the events' topical composition. (2) TCA is the only approach that extracts topics that distinctively describe meaningful parts of the dataset.</dcterms:abstract>
    <dc:creator>Zhukova, Anastasia</dc:creator>
    <dc:contributor>Zhukova, Anastasia</dc:contributor>
    <dc:contributor>Hamborg, Felix</dc:contributor>
    <dcterms:issued>2020</dcterms:issued>
    <dcterms:rights rdf:resource="https://rightsstatements.org/page/InC/1.0/"/>
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
    <foaf:homepage rdf:resource="http://localhost:8080/"/>
    <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/51922"/>
    <dcterms:title>Interpretable Topic Modeling Using Near-Identity Cross-Document Coreference Resolution</dcterms:title>
    <dc:creator>Gipp, Bela</dc:creator>
    <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2020-11-25T14:22:35Z</dcterms:available>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dc:contributor>Gipp, Bela</dc:contributor>
    <dc:creator>Hamborg, Felix</dc:creator>
    <dc:language>eng</dc:language>
  </rdf:Description>
</rdf:RDF>

Bibliography of Konstanz

No