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: | |
---|---|
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 |