Parsing with fLIF Neurons

This paper presents a natural language parsing system based solely on fatiguing Leaky Integrate and Fire neurons, a relatively faithful model of biological neurons. The parser implements cell assemblies, sequences, finite state automaton and a stack. The stack enables the system to parse context free grammars. The system uses variable binding to apply the rules, and implement the stack. A novel form of variable binding based on short term potentiation is presented. The output of the system is a semantic frame of the sentence that was parsed. The symbolic interpretation is derived from the underlying neural firing by a simple count of neurons that fire in a particular cycle. The system parses over 99% of the tested sentences correctly.

[1]  Daniel Jurafsky,et al.  An On-Line Computational Model of Human Sentence Interpretation , 1992, AAAI.

[2]  Risto Miikkulainen,et al.  Subsymbolic natural language processing - an integrated model of scripts, lexicon, and memory , 1993, Neural network modeling and connectionism.

[3]  Christian R. Huyck,et al.  Counting with neurons: rule application with nets of fatiguing leaking integrate and fire neurons. , 2006 .

[4]  Modelling Cell Assemblies , 1999 .

[5]  James Henderson,et al.  Connectionist syntactic parsing using temporal variable binding , 1994 .

[6]  Friedemann Pulvermüller,et al.  Language models based on Hebbian cell assemblies , 2006, Journal of Physiology-Paris.

[7]  Andreas Knoblauch,et al.  Pattern separation and synchronization in spiking associative memories and visual areas , 2001, Neural Networks.

[8]  Eric L. Schwartz,et al.  Computing with the Leaky Integrate-and-Fire Neuron: Logarithmic Computation and Multiplication , 1997, Neural Computation.

[9]  Christian R. Huyck,et al.  Information Retrieval and Categorisation using a Cell Assembly Network , 2005, Neural Computing & Applications.

[10]  Zenon W. Pylyshyn,et al.  Connectionism and cognitive architecture: A critical analysis , 1988, Cognition.

[11]  S. Pinker The Language Instinct , 1994 .

[12]  Christian R. Huyck,et al.  A Practical System for Human-like Parsing , 2000, ECAI.

[13]  Richard L. Lewis,et al.  An Activation-Based Model of Sentence Processing as Skilled Memory Retrieval , 2005, Cogn. Sci..

[14]  Zenon W. Pylyshyn,et al.  Connectionism and cognitive architecture , 1993 .

[15]  S. Nelson,et al.  Multiple forms of short-term plasticity at excitatory synapses in rat medial prefrontal cortex. , 2000, Journal of neurophysiology.

[16]  Alfred V. Aho,et al.  Compilers: Principles, Techniques, and Tools , 1986, Addison-Wesley series in computer science / World student series edition.

[17]  Mitchell P. Marcus,et al.  A theory of syntactic recognition for natural language , 1979 .

[18]  Michael Collins,et al.  Three Generative, Lexicalised Models for Statistical Parsing , 1997, ACL.

[19]  Christos H. Papadimitriou,et al.  Elements of the Theory of Computation , 1997, SIGA.

[20]  L. Shastri,et al.  From simple associations to systematic reasoning: A connectionist representation of rules, variables and dynamic bindings using temporal synchrony , 1993, Behavioral and Brain Sciences.

[21]  E. Capaldi,et al.  The organization of behavior. , 1992, Journal of applied behavior analysis.

[22]  Christian R. Huyck,et al.  Creating hierarchical categories using cell assemblies , 2007, Connect. Sci..