				READ ME
						Pratik Kanwal
						10524

1. Requirements
Latest 'gnu-awk' version is a must before running the script. 

2.Files
The hindi-files are :
a)l.txt	: list of 300 odd words in Hindi with their frquency written  before them ,i.e.,format is     
		frquency <space> word
b)hindi_wordlist_full_2012_12.txt  : this file, downloaded from the http://corpora.heliohost.org/ website ,is the repository of about 1 lakh Hindi words with their frequencies . 
c)slist.txt   : this is the hand annotated Hindi text file. The words in l.txt above are carefully segmented and adds one more column in the format of l.txt,i.e., a ':'(colon) followed by the correct segmentation of the word. Format is :
		frquency <space> word <colon> <word-segmentation>

3. Run
Simply run the script.sh file in the cs671 folder.
Move to its folder first and type the following command.

	>bash script.sh

Output will show the Precision, Recall and F-Score .

