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

# A. Seq2seq datasets

<div id="section1_l12" class="collapse show">
<p>With the encoder-decoder model architecture, we have a model template for any sequence to sequence NLP task. Of course, each seq2seq task will require some tweaks to the model, but overall the architecture largely stays the same across all domains.</p>
<p>The most important part to creating a good seq2seq model is finding a lot of useful training data. For machine translation, there are tons of training datasets online. You can find many of the largest machine translation datasets <a href="http://www.statmt.org/wmt18/translation-task.html" target="_blank">here</a>.</p>
<p>For training a dialog system such as a chatbot, a couple good datasets to use are the <a href="http://dataset.cs.mcgill.ca/ubuntu-corpus-1.0/" target="_blank">Ubuntu Dialogue Corpus</a> and the <a href="https://www.cs.cornell.edu/~cristian/Cornell_Movie-Dialogs_Corpus.html" target="_blank">Cornell Movie Corpus</a>.</p>
<p>For text summarization, a good training set to use is the CNN/Daily Mail summarization dataset. Instructions for how to obtain the data can be found <a href="https://github.com/abisee/cnn-dailymail" target="_blank">here</a>.</p>
</div>


# A. Seq2seq datasets

<div id="section1_l12">
<p>With the encoder-decoder model architecture, we have a model template for any sequence to sequence NLP task. Of course, each seq2seq task will require some tweaks to the model, but overall the architecture largely stays the same across all domains.</p>
<p>The most important part to creating a good seq2seq model is finding a lot of useful training data. For machine translation, there are tons of training datasets online. You can find many of the largest machine translation datasets <a href="http://www.statmt.org/wmt18/translation-task.html" target="_blank">here</a>.</p>
<p>For training a dialog system such as a chatbot, a couple good datasets to use are the <a href="http://dataset.cs.mcgill.ca/ubuntu-corpus-1.0/" target="_blank">Ubuntu Dialogue Corpus</a> and the <a href="https://www.cs.cornell.edu/~cristian/Cornell_Movie-Dialogs_Corpus.html" target="_blank">Cornell Movie Corpus</a>.</p>
<p>For text summarization, a good training set to use is the CNN/Daily Mail summarization dataset. Instructions for how to obtain the data can be found <a href="https://github.com/abisee/cnn-dailymail" target="_blank">here</a>.</p>
</div>


An overview of some useful datasets to train a seq2seq model with.

What you'll learn from this course

Word Embeddings

Language Model

Text Classification

Seq2Seq Model

Datasets

A. Seq2seq datasets