EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Flexibility in conceptual combinations: A neural network model of gradable adjective modification

Georgia-Ann Carter iD, Frank Keller, Paul Hoffman

PLOS ONE · 2024

DOI: 10.1371/journal.pone.0307775 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS ONE, 2024. Verfasst von Georgia-Ann Carter und 2 weiteren Autor:innen. Beteiligte Einrichtung: Institute for Language, Cognition and Computation, School of Informatics, Edinburgh, United Kingdom. Hauptthemen laut MEDLINE: Neural Networks, Computer, Semantics. Die Arbeit nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Biotechnology and Biological Sciences Research Council, UK Research and Innovation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Our ability to combine simple constituents into more complex conceptual combinations is a fundamental aspect of cognition. Gradable adjectives (e.g., ‘tall’ and ‘light’) are a critical example of this process, as their meanings vary depending on the noun with which they are combined. For example, a dark diamond is less dark than dark charcoal . Here, we investigate how a neural network encodes the flexible nature of gradable adjectives in adjective–noun pairs, using the perceptual feature of brightness as a test case. We trained a neural network to predict human brightness ratings for unmodified nouns and adjective–noun pairs and assessed its ability to generalize to untrained combinations (e.g., ‘light paint’ vs. ‘dark paint’). We also explored how this information is encoded. We found that flexible learning of gradable adjectives was possible, with neural networks first making predictions based on the adjective alone, and then modulating these with information from the noun later in learning. We also found that model outputs mimicked the kind of non-additive feature modulation present in human data. Our results have implications for understanding how semantic composition occurs and generate testable predictions for future work.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Neural Networks, ComputerSemanticsHumansCognitionLearning

Autor:innen und Institutionen

  • Institute for Language, Cognition and Computation, School of Informatics, Edinburgh, United Kingdom.
  • The University of Edinburgh, Edinburgh, United Kingdom.
  • School of Philosophy, Psychology and Language Sciences, Edinburgh, United Kingdom.

ORCID-Profile: Georgia-Ann Carter

Förderung

  • Biotechnology and Biological Sciences Research Council
  • UK Research and Innovation

Zitieren

APA

Carter, G. A., Keller, F., & Hoffman, P. (2024). Flexibility in conceptual combinations: A neural network model of gradable adjective modification. PLOS ONE. https://doi.org/10.1371/journal.pone.0307775

Vancouver

Carter GA, Keller F, Hoffman P. Flexibility in conceptual combinations: A neural network model of gradable adjective modification. PLOS ONE. 2024. doi:10.1371/journal.pone.0307775

BibTeX
@article{Carter2024,
  author = {Carter, Georgia-Ann and Keller, Frank and Hoffman, Paul},
  title = {Flexibility in conceptual combinations: A neural network model of gradable adjective modification},
  journal = {PLOS ONE},
  year = {2024},
  doi = {10.1371/journal.pone.0307775}
}
Kostenlos starten →