Hostname: page-component-7b7567c8c-2n9c9 Total loading time: 0 Render date: 2026-11-15T15:18:26.338Z Has data issue: false hasContentIssue false
  • English
  • Français

On the structural ambiguity in natural language that the neural architecture cannot deal with

Published online by Cambridge University Press:  15 March 2006

Rens Bod,
Hartmut Fitz and
Willem Zuidema
Rens Bod
Affiliation:
Institute for Logic, Language and Computation, University of Amsterdam, Amsterdam 1018TV, The Netherlands rens@science.uva.nl http://www.science.uva.nl/~rensSchool of Computing, University of Leeds, Leeds LS2 9JT, UK fitz@science.uva.nl http://amor.cms.hu-berlin.de/~h2784i25
Hartmut Fitz
Affiliation:
Institute for Logic, Language and Computation, University of Amsterdam, Amsterdam 1012CP, The Netherlands jzuidema@science.uva.nl http://www.science.uva.nl/~jzuidema
Willem Zuidema
Affiliation:
Institute for Logic, Language and Computation, University of Amsterdam, Amsterdam 1018TV, The Netherlands rens@science.uva.nl http://www.science.uva.nl/~rens
Rights & Permissions [Opens in a new window]

Abstract

Core share and HTML view are not available for this content. However, as you have access to this content, a full PDF is available via the 'Save PDF' action button.

We argue that van der Velde's & de Kamps's model does not solve the binding problem but merely shifts the burden of constructing appropriate neural representations of sentence structure to unexplained preprocessing of the linguistic input. As a consequence, their model is not able to explain how various neural representations can be assigned to sentences that are structurally ambiguous.

Information

Type
Open Peer Commentary
Information
Behavioral and Brain Sciences , Volume 29 , Issue 1 , February 2006, pp. 71 - 72
Copyright
© 2006 Cambridge University Press