Abstract

A natural language contains a variety of ambiguities. From a computational point of view, it is very difficult to cope with these ambiguities. Syntactic ambiguity arises from the relationship between the words and clauses of a sentence, not from the range of meanings of single words. Here, a knowledge-based adaptive approach has been proposed to resolve the syntactic ambiguities in Pashto text. The resolution involves user interaction with the system to select the appropriate meaning of the ambiguous phrase from a set of possible meanings stored in the knowledge base of the system. The user can add a new meaning to the knowledge base, for a particular phrase, if it is not there. The system has been tested on a raw Pashto corpus and resulted in accuracy of 90%.

Key words: Ambiguity, Pashto, syntactic ambiguity, syntactic ambiguity resolution, algorithm.