This Title All WIREs
How to cite this WIREs title:
WIREs Cogn Sci
Impact Factor: 2.88

Connectionist perspectives on language learning, representation and processing

Full article on Wiley Online Library:   HTML PDF

Can't access this content? Tell your librarian.

The field of formal linguistics was founded on the premise that language is mentally represented as a deterministic symbolic grammar. While this approach has captured many important characteristics of the world's languages, it has also led to a tendency to focus theoretical questions on the correct formalization of grammatical rules while also de‐emphasizing the role of learning and statistics in language development and processing. In this review we present a different approach to language research that has emerged from the parallel distributed processing or 'connectionist' enterprise. In the connectionist framework, mental operations are studied by simulating learning and processing within networks of artificial neurons. With that in mind, we discuss recent progress in connectionist models of auditory word recognition, reading, morphology, and syntactic processing. We argue that connectionist models can capture many important characteristics of how language is learned, represented, and processed, as well as providing new insights about the source of these behavioral patterns. Just as importantly, the networks naturally capture irregular (non‐rule‐like) patterns that are common within languages, something that has been difficult to reconcile with rule‐based accounts of language without positing separate mechanisms for rules and exceptions. WIREs Cogn Sci 2015, 6:235–247. doi: 10.1002/wcs.1340 This article is categorized under: Linguistics > Language Acquisition Psychology > Language Neuroscience > Computation
The TRACE model of auditory word recognition.
[ Normal View | Magnified View ]
The Seidenberg and McClelland's model of reading. Portions in black depict the model as it was originally implemented.
[ Normal View | Magnified View ]
The Rumelhart and McClelland's model of past tense.
[ Normal View | Magnified View ]
Eye‐tracking data showing competition effects from onset and rhyme competitors in a visual world paradigm. Both (a) adult listeners and (b) the TRACE model show comparable competition effects, marked by a larger proportion of eye movements to either type of phonologically related competitor relative to a phonologically unrelated foil. (Reprinted with permission from Ref . Copyright 2015 Elsevier).
[ Normal View | Magnified View ]
Lexicality effect in phoneme categorization profile of the TRACE model. The categorization of a midpoint (ambiguous) stop consonant shifts as a function of the word in which it is embedded. As in humans, the model shows a preference toward real words over a nonword, but only when the phoneme's voicing parameter is near the category boundary.
[ Normal View | Magnified View ]

Browse by Topic

Neuroscience > Computation
Psychology > Language
Linguistics > Language Acquisition

Access to this WIREs title is by subscription only.

Recommend to Your
Librarian Now!

The latest WIREs articles in your inbox

Sign Up for Article Alerts