How to execute the Code:

1. Create a project folder, say "/home/saurabh/hw2". Copy the python scripts in the folder.

2. Create a sub-directory, say "corpora" in the project folder. Copy all the Corpus files (and folder of IIT-B Copus) here.

3. Run the Preprocessing.py script. It'll ask for the Project Path. Provide the same.

4. After the script finishes, there is a folder created within the Project folder called "preprocessing".

5. Run the Segmentation.py script. This too will ask for Project folder. In addition, it'll ask for the input file on which to work, 
   the corresponding ground truth file, and the name of the output file, to be created.

6. Once the script finishes, Specs are shown as an output, and output file is created in the "output" sub-directory.

NOTE: Please remove empty lines and all kinds of punctuations from the Ground Truth File. Also, there should be a 
line-by-line matching between the input and the ground truth files.
