Why is the process of POS-tagging slow in OpenNLP?

Question

I am using OpenNLP for POS-tagging and I found out that this is incredibly slow.

  posTagger = PosModelFactory.getPosModel("en");
  String sent[] = new String[]{"Most", "large", "cities", "in", "the", "US", "had",
                             "morning", "and", "afternoon", "newspapers", "."};       
  String tags[] = posTagger .tag(sent);

I used this code for a sample of 5 sentences, and this is the time I am getting for PoS in ms.

Time taken to pos 27
Time taken to pos 11
Time taken to pos 10
Time taken to pos 11
Time taken to pos 113

Is there any way to boost this up. Any help would be appreciated.