Title :
A representational scheme for a hybrid natural language processing system
Author :
Wu, Xinyu ; McTear, Michael ; Ojha, Piyush ; Dai, Haihong
Author_Institution :
Sch. of Inf. & Software Eng., Ulster Univ., Newtownabbey, UK
Abstract :
We discuss a representational scheme used in a hybrid natural language processing system. The system is called SYMCON (Symbolic and Connectionist), and as its name implies, it consists of subsystems of different nature. SYMCON is being developed primarily for the task of word sense disambiguation (WSD). In order to disambiguate different word senses, all the necessary information (e.g., syntactic and semantic information) must firstly be represented in a machine tractable manner. Furthermore, the representations must be effective for the different subsystems in the hybrid SYMCON system to cooperate and work as whole. The representational scheme plays a crucial part in the development of the hybrid system. The system organisation of SYMCON is overviewed. Then important issues of the distributed representational scheme based on microfeatures are discussed in detail
Keywords :
natural language interfaces; natural languages; neural nets; pattern recognition; string matching; word processing; SYMCON; Symbolic and Connectionist; distributed representational scheme; hybrid natural language processing system; hybrid system; microfeatures; representational scheme; semantic information; system organisation; word sense disambiguation; Artificial intelligence; Computer science; Data mining; Dictionaries; Feature extraction; Knowledge based systems; Large-scale systems; Natural language processing; Neural networks; Software engineering;
Conference_Titel :
Systems, Man and Cybernetics, 1995. Intelligent Systems for the 21st Century., IEEE International Conference on
Conference_Location :
Vancouver, BC
Print_ISBN :
0-7803-2559-1
DOI :
10.1109/ICSMC.1995.538269