Narsil

Byte-pair encodings (BPE) are now very commonly used in NLP. In GPT-2, Byte-pair encodings are used to preformat the raw texts before feeding the model. But this is a relatively costly step for your preprocessing and has some limitations. For instance, you have to split your data…

A third of your math work is useless At Kwyk, we use AI to predict student’s performance, especially in maths. Our most recent results show that on one-third of the exercises given by the teacher we know beforehand that the student will succeed, raising the question of its usef…

When using Machine Learning to solve a problem, having the right data is crucial. Unfortunately, raw data is often “unclean” and unstructured. Natural Language Processing (NLP) practitioners are familiar with this issue as all of their data is textual. And because most of Machin…