Gaurav Arora

yes, you're right. That was a mistake when I'd first committed. I've removed those now! Thanks!

@ankur220693 not yet! Feel free to contribute and raise a PR. Let me know if you need some help along the way.

@dheerajmpai I don't think there's out of the box way in iNLTK to do this yet.

Thanks @nitkannen for your contribution. I had couple of comments: 1. It'll be great if you can remove the training code (both model and tokenizer) and push it to either...

Thanks @zehuanw for responding. It would be great to see support for Pairwise loss functions like BPR ([Paper](https://arxiv.org/ftp/arxiv/papers/1205/1205.2618.pdf)), Hinge loss ([Link](https://d2l.ai/chapter_recommender-systems/ranking.html#hinge-loss-and-its-implementation)). Let me go through the links you've shared for...