A Hidden Markov Model-Based Tagging Approach for Arabic Isnads of Hadiths

Table 2

HMM elements.

Symbol	Description
N:	Number of states
	There is a finite set of states in a model. The states in an HMM are hidden, but there is a lot of significance to these states in defining an HMM.
	The individual states are represented as S1, S2, S3, …, SN
	S = {S1, S2, S3, … , Sn}.
S:	Space of states {S1, S2, …, SN}
	N is the number of states
M:	Number of observations
	It is the number of distinct symbols observable in states. These symbols correspond to the observable output of the system that is being modeled.
	The individual states are represented as O1, O2 …, OM
O:	Space of observations {O1, O2, …, OM}
A:	Transmission probability matrix
	A is the transition array that stores the state transition probabilities
	A = {aij}, where aij stores the probability of state j following state i
B:	Emission probability matrix
	After each transition is made, a symbol is an output based on the emission probability matrix, which depends on the current state
π:	Start probability
	It is the probability of state Si being the start state in an observation sequence