Evaluating Semantic Relations in Predicting Textual Labels for Images of Abstract and Concrete Concepts
Lade...
Dateien
Datum
2024
Autor:innen
Herausgeber:innen
ISSN der Zeitschrift
Electronic ISSN
ISBN
Bibliografische Daten
Verlag
Schriftenreihe
Auflagebezeichnung
URI (zitierfähiger Link)
Internationale Patentnummer
Link zur Lizenz
Angaben zur Forschungsförderung
Projekt
Open Access-Veröffentlichung
Open Access Bookpart
Sammlungen
Core Facility der Universität Konstanz
Titel in einer weiteren Sprache
Publikationstyp
Beitrag zu einem Konferenzband
Publikationsstatus
Published
Erschienen in
KURIBAYASHI, Tatsuki, Hrsg., Giulia RAMBELLI, Hrsg., Ece TAKMAZ, Hrsg. und andere. Proceedings of the Workshop on Cognitive Modeling and Computational Linguistics. Kerrville, TX, USA: Association for Computational Linguistics, 2024, S. 214-220. ISBN 979-8-89176-143-8
Zusammenfassung
This study investigates the performance of SigLIP, a state-of-the-art Vision-Language Model (VLM), in predicting labels for images depicting 1,278 concepts. Our analysis across 300 images per concept shows that the model frequently predicts the exact user-tagged labels, but similarly, it often predicts labels that are semantically related to the exact labels in various ways: synonyms, hypernyms, co-hyponyms, and associated words, particularly for abstract concepts. We then zoom into the diversity of the user tags of images and word associations for abstract versus concrete concepts. Surprisingly, not only abstract but also concrete concepts exhibit significant variability, thus challenging the traditional view that representations of concrete concepts are less diverse.
Zusammenfassung in einer weiteren Sprache
Fachgebiet (DDC)
400 Sprachwissenschaft, Linguistik
Schlagwörter
Konferenz
The 13th edition of the Workshop on Cognitive Modeling and Computational Linguistics (CMCL 2024), 15. Aug. 2024 - 15. Aug. 2024, Bangkok, Thailand
Rezension
undefined / . - undefined, undefined
Zitieren
ISO 690
TATER, Tarun, Sabine SCHULTE IM WALDE, Diego FRASSINELLI, 2024. Evaluating Semantic Relations in Predicting Textual Labels for Images of Abstract and Concrete Concepts. The 13th edition of the Workshop on Cognitive Modeling and Computational Linguistics (CMCL 2024). Bangkok, Thailand, 15. Aug. 2024 - 15. Aug. 2024. In: KURIBAYASHI, Tatsuki, Hrsg., Giulia RAMBELLI, Hrsg., Ece TAKMAZ, Hrsg. und andere. Proceedings of the Workshop on Cognitive Modeling and Computational Linguistics. Kerrville, TX, USA: Association for Computational Linguistics, 2024, S. 214-220. ISBN 979-8-89176-143-8BibTex
@inproceedings{Tater2024Evalu-70689,
year={2024},
title={Evaluating Semantic Relations in Predicting Textual Labels for Images of Abstract and Concrete Concepts},
url={https://aclanthology.org/2024.cmcl-1.18},
isbn={979-8-89176-143-8},
publisher={Association for Computational Linguistics},
address={Kerrville, TX, USA},
booktitle={Proceedings of the Workshop on Cognitive Modeling and Computational Linguistics},
pages={214--220},
editor={Kuribayashi, Tatsuki and Rambelli, Giulia and Takmaz, Ece},
author={Tater, Tarun and Schulte Im Walde, Sabine and Frassinelli, Diego}
}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/123456789/70689">
<dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2024-08-30T10:54:04Z</dcterms:available>
<dc:creator>Frassinelli, Diego</dc:creator>
<dcterms:title>Evaluating Semantic Relations in Predicting Textual Labels for Images of Abstract and Concrete Concepts</dcterms:title>
<dc:rights>terms-of-use</dc:rights>
<dc:language>eng</dc:language>
<dcterms:hasPart rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/70689/4/Tater_2-4422lpahfzt56.pdf"/>
<dspace:hasBitstream rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/70689/4/Tater_2-4422lpahfzt56.pdf"/>
<dcterms:rights rdf:resource="https://rightsstatements.org/page/InC/1.0/"/>
<dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/45"/>
<dcterms:abstract>This study investigates the performance of SigLIP, a state-of-the-art Vision-Language Model (VLM), in predicting labels for images depicting 1,278 concepts. Our analysis across 300 images per concept shows that the model frequently predicts the exact user-tagged labels, but similarly, it often predicts labels that are semantically related to the exact labels in various ways: synonyms, hypernyms, co-hyponyms, and associated words, particularly for abstract concepts. We then zoom into the diversity of the user tags of images and word associations for abstract versus concrete concepts. Surprisingly, not only abstract but also concrete concepts exhibit significant variability, thus challenging the traditional view that representations of concrete concepts are less diverse.</dcterms:abstract>
<dc:contributor>Schulte Im Walde, Sabine</dc:contributor>
<dcterms:issued>2024</dcterms:issued>
<foaf:homepage rdf:resource="http://localhost:8080/"/>
<dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2024-08-30T10:54:04Z</dc:date>
<dc:contributor>Frassinelli, Diego</dc:contributor>
<void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
<dc:creator>Tater, Tarun</dc:creator>
<dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/45"/>
<bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/70689"/>
<dc:contributor>Tater, Tarun</dc:contributor>
<dc:creator>Schulte Im Walde, Sabine</dc:creator>
</rdf:Description>
</rdf:RDF>Interner Vermerk
xmlui.Submission.submit.DescribeStep.inputForms.label.kops_note_fromSubmitter
URL der Originalveröffentl.
Prüfdatum der URL
2024-08-30
