Define and explain Word Embedding with Global Vectors (GloVe).

Save pretrained GloVe embeddings of dimension 50 from GloVe website. Write a Python class to load the 50-dimensional GloVe embeddings.

Write a function to implement the following KNN (K-Nearest Neighbors) to find semantically similar words for an input word based on cosine similarities between word vectors. Write a function to search for similar words using the pretrained word vectors from the TokenEmbedding instance embed.

Get three similar tokens for word 'chip'.

Include your working Python programming code and program final results in your CT required assignment document.

Attach your Jupyter notebook Python (ipynb) file as well as your CT required assignment document.

Feel free to use and refactor the module example code.