What Counts as an Exemplar Model, Anyway? A Commentary on Ambridge (2020)

Autor/inn/en	Mahowald, Kyle; Kachergis, George; Frank, Michael C.
Titel	What Counts as an Exemplar Model, Anyway? A Commentary on Ambridge (2020)
Quelle	In: First Language, 40 (2020) 5-6, S.608-611 (4 Seiten)Infoseite zur Zeitschrift PDF als Volltext Verfügbarkeit
Zusatzinformation	ORCID (Kachergis, George)
Sprache	englisch
Dokumenttyp	gedruckt; online; Zeitschriftenaufsatz
ISSN	0142-7237
DOI	10.1177/0142723720905920
Schlagwörter	Models; Language Processing; Computational Linguistics; Language Acquisition; Natural Language Processing; Linguistic Input; Abstract Reasoning; Linguistic Theory; Computer Software; Artificial Intelligence; Syntax; Figurative Language; Memory + Suchen Sie Ihr Suchwort? Analogiemodell; Sprachverarbeitung; Linguistics; Computerlinguistik; Sprachaneignung; Spracherwerb; Natürliche Sprache; Sprachbildung; Abstraktes Denken; Denken; Linguistische Theorie; Künstliche Intelligenz; Gedächtnis
Abstract	Ambridge calls for exemplar-based accounts of language acquisition. Do modern neural networks such as transformers or word2vec -- which have been extremely successful in modern natural language processing (NLP) applications -- count? Although these models often have ample parametric complexity to store exemplars from their training data, they also go far beyond simple storage by processing and compressing the input via their architectural constraints. The resulting representations have been shown to encode emergent abstractions. If these models are exemplar-based then Ambridge's theory only weakly constrains future work. On the other hand, if these systems are not exemplar models, why is it that true exemplar models are not contenders in modern NLP? [For Ben Ambridge's "Against Stored Abstractions: A Radical Exemplar Model of Language Acquisition," see EJ1269951.] (As Provided).
Anmerkungen	SAGE Publications. 2455 Teller Road, Thousand Oaks, CA 91320. Tel: 800-818-7243; Tel: 805-499-9774; Fax: 800-583-2665; e-mail: journals@sagepub.com; Web site: http://sagepub.com
Erfasst von	ERIC (Education Resources Information Center), Washington, DC
Update	2024/1/01