My final year undergraduate project at the University of Manchester. It is a question and answer system built using off the shelf libraries, for the purpose of querying legal documents.
Run the following command in the terminal:
pip3 install -r requirements.txt
Next, in order to get the necessary list of nltk stopwords, complete the following steps:
1. Open the Python interpreter by typing 'python' in the terminal.
2. Enter command "import nltk".
3. Enter command "nltk.download('stopwords')"
4. Close the Python interpreter.
When running the code for the absolute first time the following steps must be followed:
1. Enter command "cd src"
2. Enter command "python3 ModelLoader.py"
3. Enter command "python3 MatrixLoader.py" and provide the path "../Training Documents" at the input prompt. (This may take a few hours to run, in order to build the similarity matrix.)
4. Enter command "python3 FinalProject.py" and follow the prompts.
On subsequent runs of FinalProject.py, you will only need to complete step 4 above.
The similarity matrix can be updated by running MatrixLoader.py and providing the path to the directory you wish to build the matrix with.