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

To allow the model to classify longer input text sequences

To make the word embeddings more accurate for the text corpus

To improve model performance compared to a regular LSTM/BiLSTM

To generate an output sequence based on an input sequence

What's the main purpose of using an encoder-decoder model?

What’s the main purpose of using an encoder-decoder model?

It helps the model create better word embeddings based on word context

It allows the model to focus on important parts of an input sequence when decoding

It allows the model to train faster since it only performs attention computations

In a BiLSTM each cell goes both forwards and backwards

What is the purpose of attention in an encoder-decoder model?

What is the purpose of attention in an encoder-decoder model?

We don't use embeddings during inference, so we use a different Sampler

The TrainingSampler allows us to run the model faster during training

During training the model has access to ground truth tokens, but not during inference

We can only use the sample_id property with the inference Sampler

Why do we use different Sampler objects for training and inference?

Why do we use different Sampler objects for training and inference?

This ensures that the decoder will always return at least one token

When the decoder outputs a stop token, it lets us know that the decoding is done

It is necessary to use a stop token because we use the start token

The stop token lets the encoder know that the input sequence is finished

What is the main purpose of the stop token for encoder-decoder models?

What is the main purpose of the stop token for encoder-decoder models?

What you'll learn from this course

Word Embeddings

Language Model

Text Classification

Seq2Seq Model

Quiz