Gain insights into processing text data, creating word embeddings, and using LSTMs for semantic analysis and machine translation. Explore industry-relevant NLP techniques with Python and TensorFlow.

nlp_docker.tar.gz

mnist-fashion

In this course you'll learn techniques for processing text data, creating word embeddings, and using long short-term memory networks (LSTM) for tasks such as semantic analysis and machine translation. After completing this course, you will be able to solve the important day-to-day NLP problems faced in industry, which is incredibly useful given the prevalence of text data.

The code for this course is built around the TensorFlow framework, one of the premier frameworks for industry machine learning, and the Python pandas library for data analysis. Knowledge of Python and TensorFlow are prerequisites. 

This course was created by AdaptiLab, a company specializing in evaluating, sourcing, and upskilling enterprise machine learning talent. It is built in collaboration with industry machine learning experts from Google, Microsoft, Amazon, and Apple.

Natural Language Processing with Machine Learning

Analyzing the main purpose of a sentence in a text passage

Analyzing a writer's attitude based on the text passage

Analyzing the differences between two text passages

The BiLSTM combines both a forwards and backwards LSTM

The BiLSTM uses two cell layers while a regular LSTM uses one

The regular LSTM can only take in one text sequence per iteration

In a BiLSTM each cell goes both forwards and backwards

What differentiates a bidirectional LSTM (BiLSTM) from a regular LSTM?

What differentiates a bidirectional LSTM (BiLSTM) from a regular LSTM?

A BiLSTM uses fewer parameters and therefore trains quicker

A BiLSTM can look at the entire input sequence while a regular LSTM cannot

A BiLSTM looks at both the past and future context of phrases in a text passage

We don't need to use padding when using a BiLSTM

What is the main reason a BiLSTM usually works better than a regular LSTM?

What is the main reason a BiLSTM usually works better than a regular LSTM?

For classification we only take each sequence's final time step LSTM output

For classification we can only use a BiLSTM model

The logits in language modeling are integer values instead of floats

The logits for classification are strictly positive values

What is the main difference in how we calculate logits for language modeling vs. classification?

What is the main difference in how we calculate logits for language modeling vs. classification?

What you'll learn from this course

Word Embeddings

Language Model

Text Classification

Seq2Seq Model

Quiz