GloVe is an unsupervised learning algorithm for obtaining vector representations of words. The training is performed on the aggregate global statistics on the co-occurrence of words that has been extracted from a body of text present in the code files. The resulting representations show interesting linear substructures in the vector space of words. In this recipe, you will learn how to use a pretrained GloVe embedding model to classify adjectives to describe a person in a positive or negative fashion.
Transfer learning with pretrained GloVe embedding
Getting ready
To follow this recipe, you will need to download the glove.6B.100d.txt file. This file is available at https://nlp.stanford.edu/projects/glove/. There are several...
