Kavita’s Articles

One of the questions that often comes up is what’s the difference between fastText and Word2Vec? Aren’t they both the same? Yes and no. They are conceptually the same, but there is a minor difference—fastText operates at a character…

Word2Vec is a widely used word representation technique that uses neural networks under the hood. The resulting word representation or embeddings can be used to infer semantic similarity between words and phrases, expand queries, surface related concepts…

Previously, we learned how to use CountVectorizer for text processing. In place of CountVectorizer, you also have the option of using HashingVectorizer. In this tutorial, we will learn how HashingVectorizer differs from CountVectorizer and when to use…

Scikit-learn’s CountVectorizer is used to transform a corpora of text to a vector of term / token counts. It also provides the capability to preprocess your text data prior to generating the vector representation making it a…

Text classification is the automatic process of predicting one or more categories given a piece of text. For example, predicting if an email is legit or spammy. Thanks to Gmail’s spam classifier, I don’t see or hear…

What are pre-trained embeddings and why? Pre-trained word embeddings are vector representation of words trained on a large dataset. With pre-trained embeddings, you will essentially be using the weights and vocabulary from the end result of the…