                                                                              
                         *********** CFILT Hindi POS Tagger***********




>This POS tagger is developed at the CFILT department of Indian Institute Of Technology, Bombay, India.

>This is a CRF based POS Tagger for Hindi Language. This tagger uses CRF based open source tool-kit CRF++. The toolkit is there in the folder. You can also get the tool-kit from- http://crfpp.sourceforge.net/

>CRF++ tool-kit is used to POS tag the input text. Text Files  can't be used directly for testing using the CRF++ package. 

>Instruction to install the tagger are in INSTALL.txt. 

>Following are the  instructions to get the input text POS tagged.
 Suppose path of the extracted system is -"/home/xyz/abc/POS_tagger/".


  Step1 : System takes the input as "word_[ tag ]" format. If your input is not tagged then first input text(test_file.txt) should be tokenized. Run-

          :~$sh /home/xyz/abc/POS_tagger/tokenize.sh test_file.txt > file1.txt

  Step2 : Run the script pos.sh in the folder.
	  :~$sh /home/xyz/abc/POS_tagger/pos.sh <tagged_input_file>
	The result file will be <tagged_input_file>_final
 
         - <tagged_input_file>_final file contains the POS tagged text.          

****************************************************************END******************************************************************************************

