Link to problem statement: https://pan.webis.de/clef17/pan17-web/author-clustering.html
Link to published Paper: https://dl.acm.org/doi/abs/10.1145/3368567.3368572
- Please use Quick_main.py to quickly run the project using the saved vectors for the documents in each problem folder.
- You can also take the benefit of the Quick_main.ipynb.
- Note: You may set the path according to your diretory of the access. If there is Error because of the path for the required files.
For Training you may peek into main.py
- GoogleNews-vectors-negative300.bin.gz
- wiki.nl.bin
- wiki.el.bin