Newsgroups: comp.ai.neural-nets
Path: cantaloupe.srv.cs.cmu.edu!rochester!cornell!travelers.mail.cornell.edu!news.kei.com!news.mathworks.com!uhog.mit.edu!bloom-beacon.mit.edu!gatech!howland.reston.ans.net!math.ohio-state.edu!scipio.cyberstore.ca!vanbc.wimsey.com!news.bc.net!newsserver.sfu.ca!fornax!hadley
From: hadley@cs.sfu.ca (Bob Hadley)
Subject: Systematicity, Representation, and Learning
Message-ID: <1994Nov14.204125.11174@cs.sfu.ca>
Keywords: systematicity, compositionality, representation, learning
Organization: Simon Fraser University
Distribution: na
Date: Mon, 14 Nov 1994 20:41:25 GMT
Lines: 44



                        Strong Semantic Systematicity
				    from
                      Unsupervised Connectionist Learning

                                     by

                        Robert F. Hadley and Michael Hayward
                            School of Computing Science
                               Simon Fraser University

                               CSS-IS TR94-02 

                                   ABSTRACT

A network exhibits strong semantic systematicity just in case, as
a result of training, it can assign  appropriate  meaning
representations to simple and embedded sentences which contain
words in syntactic positions they did not occupy during training.  
The experience of researchers indicates that strong systematicity
in any form is difficult to achieve in connectionist
systems.  Herein we describe a network which displays strong
semantic systematicity in response to *unsupervised*
training.  In addition, the network generalizes to novel levels
of embedding.  Successful training requires a corpus of about
1000 sentences, and network training is quite rapid.  The
architecture and learning algorithms are purely connectionist,
but `classical' insights are discernible in one respect, viz.,
that complex semantic representations spatially contain their
semantic constituents.  However, in other important respects,
representations are distinctly non-classical.  


        The above is available as a PS file by email.  
        Also available by FTP upon request.  Please contact
	hadley@cs.sfu.ca for FTP directions.

  My apologies for reposting this abstract, but the original posting
  seems to have disappeared after just a few days.  Perhaps we have some
  local bug here at SFU, but we can find the original posting.

  Bob Hadley

