A Comparative Study of Some Automatic Arabic Text Diacritization Systems

Algorithm 4

create_Distribution_Of_Letter_3-grams_Having_A_Successor.

(i)	//Extract the 3-gram letters that have a successor to form the 4-grams.
(ii)	//This method can be used when calculating the Absolute Discount Smoothing
(iii)	Input: list of diacritized 4-grams grams,//each 4-gram is a tuple
(iv)	Output: a dictionary d representing the distribution of 3-gram letters that have a successor
(v)	SET unzip EQUAL TO EMPTY LIST
(vi)	SET n_minus_one_grams EQUAL TO EMPTY LIST
(vii)	SET d EQUAL TO EMPTY DICTIONARY
(viii)	unzip: = LIST(zip(grams))//Unzip the grams into 4 tuples
(ix)	unzip.pop()//delete the last tuple
(x)	n_minus_one_grams: = zip(unzip[0], unzip [1], unzip [2])
(xi)	d: = freqDist(list(n_minus_one_grams))
(xii)	RETURN d