 |
Design and implementation of a software system for detecting orthographical or morphological errors in Persian words
Hamid Hassanpour and Ibrahim Hallajian
Azad University, Ghaemshar, Iran
With the advance of natural language processing techniques and expansion use of computer, vast investigations are performed in many languages to find orthographical and structural errors in a context. Testing orthography correctness and morphology consistency of words propound as one of the application of natural language processing.
This paper presents a new method for analyzing words in Persian context to find the orthographical and structural errors regardless of the meaning. This technique tokenizes the words in a statement then tries to detect the kind of word, and analyses their correctness in terms of orthography and morphology by means of lexicon. It may need to be noted that some words in Persian language have the same stem, which are constructed based on the rules by adding particles to them. For this we present a new method to reduce the size/volume of the lexicon and to quicken in searching.
|
