Slaapte or Sliep? Extending Neural-Network Simulations of English Past Tense Learning to Dutch and German
Year: 2023
Type: article
Abstract: This work studies the plausibility of sequence-to-sequence neural networks as models of morphological acquisition by humans.We replicate the findings of Kirov and Cotterell (2018) on the wellknown challenge of the English past tense and examine their generalizability to two related but morphologically richer languages, namely Dutch and German.Using a new dataset of English/Dutch/German (ir)regular verb forms, we show that the major findings of Kirov and Cotterell (2018) hold for all three languages, including the observation of over-regularization errors and micro U-shape learning trajectories.At the same time, we observe troublesome cases of non human-like errors similar to those reported by recent followup studies with different languages or neural architectures.Finally, we study the possibility of switching to orthographic input in the absence of pronunciation information and show this can have a nonnegligible impact on the simulation results, with possibly misleading findings.
Authors: Yang, Xiulin, Chen, Jingyan, Eerden, Arjan van, Samin, Ahnaf Mozib, Bisazza, Arianna
Institution: University of Groningen
Language: English
Subfield: Developmental and Educational Psychology
Field: Psychology
Domain: Social Sciences
Open Access status: green
OpenAlex ID: W7052495744
FWCI:
Cites:
Cited by:
Related to: