an abstract to post

[Bob Hadley]

Hi,

I'd be grateful if someone could post this abstract on the 
Connectionist List.

Thanks,
  --------------------------------------------------------------------
  Robert F. Hadley (Bob)              Phone: 604-291-4488
  Associate Professor                 email: hadley at cs.sfu.ca
  School of Computing Science         
  Simon Fraser University
  Burnaby, B.C. V5A 1S6
  Canada

------------------------------------------------------------
FTP-host: ftp.fas.sfu.ca
FTP-filename: /pub/cs/hadley/act.pas.ps

          The following paper is available by FTP and on the WWW.
               	         (instructions below)
                -------------------------------------                 

               Acquisition of the Active-Passive Distinction 
                  from Sparse Input and No Error Feedback

                                    by

                     Robert F. Hadley and Vlad C. Cardei



                         School of Computing Science 
                           Simon Fraser University 
                               Burnaby, B.C.
                              V5A 1S6   Canada 
                      hadley at cs.sfu.ca  vcardei at cs.sfu.ca 

                       Technical Report -- CSS-IS TR 97-01 

  
ABSTRACT

A  connectionist-inspired, parallel processing network is
presented which learns, on the basis of (relevantly) sparse
input, to assign meaning interpretations to *novel* test
sentences in both active and passive voice.   Training and test
sentences are generated from a simple recursive grammar, but once
trained,  the network successfully processes thousands of
sentences containing deeply embedded clauses.  All training is
unsupervised with regard to error feedback -- only Hebbian and
Kohonen forms of training are employed.  In addition, the
active-passive distinction is acquired without any supervised
provision of cues or flags (in the output layer)  that indicate
whether the input sentence is in active or passive sentence. 
In more detail: (1) The model learns on the basis of a corpus of
about 1000 sentences while the set of potential test sentences
contains over 100 million sentences.  (2) The model generalizes
its capacity to interpret active and passive sentences to
substantially deeper levels of clausal embedding.  (3)  After
training, the model satisfies criteria for strong syntactic and
strong semantic *systematicity* that humans also satisfy. (4)
Symbolic message passing occurs within the model's output layer. 
This symbolic aspect reflects certain prior *language acquistion*
assumptions. 

   
		   (60 pages, 1.2 spacing)

-----------------------------------------------------------

You can obtain the above paper via ftp by doing the following:

    ftp   ftp.fas.sfu.ca

    When asked for your name, type the word:  anonymous  

    When asked for a password, use your e-mail address.

    Then, you should change directory as follows:


	 cd  pub/cs/hadley
	 
	 and then do a get, as in:

	 get act.pas.ps
	 
  To exit from ftp, type : quit  

..................

Also, available using web brousers at:

      http://fas.sfu.ca/cs/people/GradStudents/vcardei/personal/Projects/