Exploiting Semantic Annotations and -Learning for Constructing an Efficient Hierarchy/Graph Texts Organization

Algorithm 3

SALA_links algorithm.

Input: Action_type, and Feature_Vertex Object(FVO)

Output: Detect Links between Feature Vertices and assigned the Features_Link Weight(FLW).

Procedure

{ i ← index of the FVO input in FLG;

numVerts ← number of Feature_Vertex objects (FVO) in Vertex ()

 for (int  numVerts; j++)

  if (Action_type == “Closest-Synonyms”)then

  {Fsyn = get_ C-SynD (FVO[]); /^* Function to execute C-SynD algorithm. /^*

  if(FVO[].contain(Fsyn)) then

  { FLW← SemRel(FVO[], FVO[]) /^*Function to compute the value of semantic relatedness between

  the FVO[] and FVO[]. /^*

   Rel-Type ← 5; /^* set the relation type with 5 indicates of synonym. /^*

   }

  }

  elseif(Action_type == “Association”)then

  { optimal_action = get_ IOAC-QL (FVO);/^* Function to execute IOAC-QL algorithm. /^*

  FLW ← reward; /^* The reward value of optimal action returned/^*

  Rel-Type ← action_type; /^* The type of optimal action returned (type = 1 for similarity, type = 2 for contiguity,

  type = 3 for contrast, type = 4 for causality) /^*

  }

  Rel_vertex = ; /^* index of the related vertex. /^*

  Adjacent[] = FLW; /^*set the value of linkage weight in adjacency matrix between related vertex [], vertex []. /^*

}