A psycholinguistic model of natural language parsing implemented in simulated neurons.
Huyck, Christian R. (2009) A psycholinguistic model of natural language parsing implemented in simulated neurons. Cognitive Neurodynamics, 3 (4). pp. 316-330. ISSN 1871-4080
PDF (Neural Parser pdf)
- Published version (with publisher's formatting)
A natural language parser implemented entirely in simulated neurons is described. It produces a semantic representation based on frames. It parses solely using simulated fatiguing Leaky Integrate and Fire neurons,
that are a relatively accurate biological model that is simulated efficiently. The model works on discrete cycles that simulate 10 ms. of biological time, so the parser has a simple mapping to psychological parsing time. Comparisons to human parsing studies show that the parser closely approximates this data. The parser makes use of
Cell Assemblies and the semantics of lexical items is represented by overlapping hierarchical Cell Assemblies so that semantically related items share neurons. This semantic encoding is used to resolve prepositional phrase attachment ambiguities encountered during parsing. Consequently, the parser provides a neurally-based cognitive model of parsing.
|Research Areas:||A. > School of Science and Technology > Computer Science
A. > School of Science and Technology > Computer Science > Artificial Intelligence group
|Depositing User:||Chris Huyck|
|Date Deposited:||02 Mar 2010 14:41|
|Last Modified:||13 Oct 2016 14:17|
Actions (login required)