Heads up! Looks like you're using adblock. Please consider supporting us by whitelisting coursedio.online How?

file_download Exercise Files

Next Video arrow_forward

What makes doc2vec powerful?

with Derek Jedamski

Build upon your foundational knowledge of natural language processing (NLP) by exploring more complex topics such as word2vec, doc2vec, and recurrent neural networks.

play_circle_filled

Leveraging the power of messy text data

play_circle_filled

What you should know

play_circle_filled

What tools you need

play_circle_filled

Using the exercise files

play_circle_filled

What is NLP?

play_circle_filled

NLTK setup

play_circle_filled

Reading text data into Python

play_circle_filled

Cleaning text data

play_circle_filled

Vectorize text using TF-IDF

play_circle_filled

Building a model on top of vectorized text

play_circle_filled

What is word2vec?

play_circle_filled

What makes word2vec powerful?

play_circle_filled

How to implement word2vec

play_circle_filled

How to prep word vectors for modeling

play_circle_filled

What is doc2vec?

play_circle_filled

What makes doc2vec powerful?

play_circle_filled

How to implement doc2vec

play_circle_filled

How to prep document vectors for modeling

play_circle_filled

What is a neural network?

play_circle_filled

What is a recurrent neural network?

play_circle_filled

What makes RNNs so powerful for NLP problems?

play_circle_filled

Preparing data for an RNN

play_circle_filled

How to implement a basic RNN

play_circle_filled

Prep the data for modeling

play_circle_filled

Build a model on TF-IDF vectors

play_circle_filled

Build a model on word2vec embeddings

play_circle_filled

Build a model on doc2vec embeddings

play_circle_filled

Build an RNN model

play_circle_filled

Compare all methods using key performance metrics

play_circle_filled

Key takeaways for advanced NLP modeling techniques

play_circle_filled

How to continue advancing your skills