Systematicity, Hebbian Learning, Lang. Acquis.

[Bob Hadley]

                     The following paper is available at:

	                   www.cs.sfu.ca/~hadley/online.html

                       Total pages: 37 at 1.6 spacing.



         Syntactic Systematicity Arising from Semantic Predictions 
                   in a Hebbian-Competitive Network 
 
                                     BY 

                               Robert F. Hadley
                              Adam Rotaru-Varga
                               Dirk V. Arnold
                               Vlad C. Cardei




                          School of Computing Science,
                          Simon Fraser Burnaby, B.C.,
                               V5A 1S6   Canada  


  
                              ABSTRACT


 A Hebbian-inspired, competitive network is presented which 
learns to predict the typical semantic features of  denoting
terms in simple and moderately complex sentences.   In addition,
the network learns to predict the appearance of syntactically key
words, such as prepositions and relative pronouns.   
Importantly, as a by-product of the network's semantic training, 
a strong form of  syntactic systematicity  emerges. This
systematicity is exhibited even at a novel, deeper level of
clausal embedding.  All network training is unsupervised with
respect to error feedback.  A novel variant of competitive
learning, and an unusual hierarchical architecture are presented. 
The relationship of this work to issues raised by Marcus (1998)
and Phillips (2000) is explored.

 

 Keywords: Systematicity, Semantic Features, Language Acquisition, 
		   Competitive Learning, Connectionism.