CLoAn -- Contrastive Loanword Annotator

What is CLoAn?

CLoAn stands for Contrastive Loanword Annotator. It is an annotation tool to create contrastive bitext, with one side containing loanwords and the other only "native" alternatives. It is part of my Bachelor's Thesis.

Installing

To use CLoAn, clone this repository in a directory of your choice:

    git clone git@github.com:chamisshe/CLoAn.git

Next, you'll want to run the included setup-scripts. This will create a virtual environment, install the required packages and create the necessary folder structure.

Mac/Linux

On a UNIX-based system, run the following commands:

    cd CLoAn
    source setup.sh

Windows

On Windows (CMD or PowerShell), run:

    cd CLoAn
    setup.bat

Installing the Flores+ dataset

You will most likely will work with the devtest split of the FLORES+ dataset. We cannot host the dataset on a public repository, therefore you will have to download the dataset from it's source repository yourself.
Important: Keep track of the path where you stored it, as you'll need to tell CLoAn when you use the tool for the first time.

Bugs and other Issues

CLoAn is by no means bug-free (barely any software is). Bugs encountered during development are mostly accounted for and handled, but that most likely doesn't include every possible edge case. For any bugs or inconveniences you may encounter, or suggestions for improvement, you can either open an Issue or write me an email.