In this project we are tryinbg to create unredactor. Unredactor will take a redacted document and the redacted flag as input, inreturn it will give the most likely candidates to fill in redacted location. In this project we are only considered about unredacting names only. The data that we are considering is imdb data set with many review files. These files are used to buils corpora for finding tfidf score. Few files are used to train and in these files names are redacted and written into redacted folder. These redacted files are used for testing and different classification models are built to predict the probabilies of each class. Top 5 classes i.e names similar to the test features are written at the end of text in unreddacted foleder.
Why do you think that https://github.com/benedekrozemberczki/awesome-gradient-boosting-papers is a good alternative to Unredactor