Abstract: | I survey some recent applications-oriented NL generation systems, and claim that they have a remarkably similar architecture in terms of the modules they divide the generation process into, the computations these modules perform, and the way the modules interact with each other. This similarity is surprising given the different theoretical bases of the examined systems, especially since in some cases the relevant theories argue against aspects of this 'consensus' architecture. I furthermore argue that the consensus architecture is more physcholinguistically plausible than some of the architecture developed in more theoretically motivated work, despite the fact that psycholinguistic plausibility was not in general a goal of the developers of the examined systems; perhaps (being somewhat speculative), this convergence is due to a similarity in 'goals' between applications-systems builders and the evolutionary processes that created the human language processor.
|