Word representations
Word representations
- Level
- Basic (22 points)
In this lab you will implement the skip-gram model with negative sampling (SGNS) from Lecture 2.04, and use it to train word embeddings on the text of the Simple English Wikipedia.
- Link to the basic lab
- Blog post on Sampling words by frequency
Under the hood of the CBOW classifier
- Level
- Advanced (22 points)
In Lecture 2.03 you learned about the CBOW classifier. This classifier is easy to implement in PyTorch with its automatic differentiation magic; but it is easy also to forget about what is going on under the hood. Your task in this lab is to implement the CBOW classifier without any magic, using only a library for vector operations (NumPy).