Modeling the Role of Polysemy in Verb Categorization
Experiments in Linguistic Meaning · 27.01.2023 · 2 · 278
DOI: 10.3765/elm.2.5379 ↗Kurz gefasst
Fachartikel in der Zeitschrift Experiments in Linguistic Meaning, online erschienen am 27.01.2023. Verfasst von Elizabeth Soper und 1 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Recent work has indicated that static word embeddings can predict human semantic categories (Majewska et al. 2021). In this paper, we consider the role of polysemy in semantic categorization, by comparing sense-level embeddings with previously studied static embeddings in their prediction of human-produced categories. We find that the polysemy is crucial for predicting human categories; sense-level embeddings dramatically outperform static embeddings in predicting semantic categories. Our findings highlight the role of polysemy in semantic categorization that is exclusively based on linguistic input.
Zitieren
APA
Soper, E., & Koenig, J. (2023). Modeling the Role of Polysemy in Verb Categorization. Experiments in Linguistic Meaning, 2, 278. https://doi.org/10.3765/elm.2.5379
Vancouver
Soper E, Koenig J. Modeling the Role of Polysemy in Verb Categorization. Experiments in Linguistic Meaning. 2023;2:278. doi:10.3765/elm.2.5379
BibTeX
@article{Soper2023,
author = {Soper, Elizabeth and Koenig, Jean-Pierre},
title = {Modeling the Role of Polysemy in Verb Categorization},
journal = {Experiments in Linguistic Meaning},
year = {2023},
volume = {2},
pages = {278},
doi = {10.3765/elm.2.5379}
}
EUVIMED