A natural language parser which has been successfully implemented is described. This is a hybrid system, in which neural networks operate within a rule based framework. It can be accessed via telnet for users to try on their own text. (For details, contact the author.) Tested on technical manuals, the parser finds the subject and head of the subject in over 90% of declarative sentences. The neural processing components belong to the class of Generalized Single Layer Networks (GSLN). In general, supervised, feed-forward networks need more than one layer to process data. However, in some cases data can be pre-processed with a non-linear transformation, and then presented in a linearly separable form for subsequent processing by a single layer net. Such networks offer advantages of functional transparency and operational speed. For our parser, the initial stage of processing maps linguistic data onto a higher order representation, which can then be analysed by a single layer network. This transformation is supported by information theoretic analysis.