NotesFAQContact Us
Collection
Advanced
Search Tips
Showing all 3 results Save | Export
Peer reviewed Peer reviewed
Direct linkDirect link
Mahowald, Kyle; Kachergis, George; Frank, Michael C. – First Language, 2020
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…
Descriptors: Models, Language Processing, Computational Linguistics, Language Acquisition
Peer reviewed Peer reviewed
PDF on ERIC Download full text
Jones, Michael N. – Grantee Submission, 2018
Abstraction is a core principle of Distributional Semantic Models (DSMs) that learn semantic representations for words by applying dimensional reduction to statistical redundancies in language. Although the posited learning mechanisms vary widely, virtually all DSMs are prototype models in that they create a single abstract representation of a…
Descriptors: Abstract Reasoning, Semantics, Memory, Learning Processes
Peer reviewed Peer reviewed
Direct linkDirect link
Schuler, Kathryn D.; Kodner, Jordan; Caplan, Spencer – First Language, 2020
In 'Against Stored Abstractions,' Ambridge uses neural and computational evidence to make his case against abstract representations. He argues that storing only exemplars is more parsimonious -- why bother with abstraction when exemplar models with on-the-fly calculation can do everything abstracting models can and more -- and implies that his…
Descriptors: Language Processing, Language Acquisition, Computational Linguistics, Linguistic Theory