For cleaning corpus:
1)compile the clean.java file
	javac clean.java
2)run the java file to clean the uncleaned corpus
	javac clean >clean_corpus.txt
3)After giving the above command give the file name to be cleaned
	unclean_corpus.txt

For calculating hits, misses and recall:
1)keep the files finalSegmentation.txt,list16.txt and eval.py the in same directory.
2)Run the eval.py file.
3) returns 3 integers. 1st line is hits, 2nd line is insertions and 3rd line is deletions. 