The Learnability of the Wh-Island Constraint in Dutch by a Long Short-Term Memory Network

The current study investigates whether a Long Short-Term Memory (LSTM) network can learn the wh-island constraint in Dutch in a way comparable to human native speakers. After establishing with an acceptability judgement task that native speakers demonstrate a clear sensitivity to wh-island violations, the LSTM network was tested on the same sentences. Contrary to the results of the native speakers, the network was not able to recognize wh-islands and to block gap expectancies within them. This suggests that input and the network’s inductive biases alone might not be enough to learn about synta... Mehr ...

Verfasser: Suijkerbuijk, Michelle
Frank, Stefan L.
de Swart, Peter
Dokumenttyp: posted-content
Erscheinungsdatum: 2023
Verlag/Hrsg.: Center for Open Science
Sprache: unknown
Permalink: https://search.fid-benelux.de/Record/base-27081816
Datenquelle: BASE; Originalkatalog
Powered By: BASE
Link(s) : http://dx.doi.org/10.31234/osf.io/njr3z