Introduction:

This paper collects those arguments which are in my view crucial for further progress and is intended only as a reminder of insights which might have been forgotten for some time. Research on discourse has achieved remarkable results in the past decade. The standard has been raised from simple question answering to dialogue facilities; a fact which, as we all know, implies much more than only extending the borderline of syntactic analysis to the level of more than one sentence and more than one speaker. However, at the same time we all know that the reality of discourse is nearly as far away as before from what we are able to model now. It's certainly not worth enumerating now all the deficiencies of current models and to list what the real goals are. It's a matter of every-day experience to see the "blatant mismatch between superficial human ease and theoretical mechanical intractability" as Berwick stated in Brady and Berwick's book. How did Artificial Intelligence react to this fact?

You will receive

    file format: rtf
    encryption: gzip
    size: 26k
 

In case of any problems please send a mail to vhahn@informatik.uni-hamburg.de