Base Architectures for NLP
Tom Mahieu, Stefan Raeymaekers, Karel De Vlaminck, Gerda Janssens, Wouter Joosen · Lirias · 1998
Our goal is to develop an object-oriented framework for natural language processing (NLP). With this framework it should be possible to create a variety of applications ranging from simple spelling checkers to complex translation systems, just by plugging different components (e.g. a morphological lookup component, chart parser component, etc) in the framework. This paper compares two base architectures that can form the core of such an NLP system. The first one considers NLP from a processing point of view (a text gets processed), the second one from a text point of view (a text processes itself). Some important considerations are made on how configurable and open the system is. Considerations to make the system concurrent and distributed to obtain better performance are also discussed. 1