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

<h2 class="section-title">Chapter Goals:</h2>
<ul>
	<li>Combine the final states for each BiLSTM layer</li>
</ul>


<h2>A. LSTMStateTuple initialization</h2>

<div id="section1_l3" class="collapse show">
<p>We initialize an <code>LSTMStateTuple</code> object with a hidden state (<code>c</code>) and state output (<code>h</code>).</p>
<p>Below we show an example of initializing an <code>LSTMStateTuple</code> object using the final forward and backward states from a single layer BiLSTM encoder.</p>

import tensorflow as tf

# Forward state of single-layer BiLSTM final states
fw_c = forward_final_state[0]
fw_h = forward_final_state[1]

# Backward state of single-layer BiLSTM final states
bw_c = backward_final_state[0]
bw_h = backward_final_state[1]

# Concatenate along final axis
final_c = tf.concat([fw_c, bw_c], -1 )
final_h = tf.concat([fw_h, bw_h], -1)

combined_state = tf.compat.v1.nn.rnn_cell.LSTMStateTuple(
    final_c, final_h)

print(combined_state)

In the above example, we combined the BiLSTM forward and backward states into a single <code>LSTMStateTuple</code> object, which can be passed into the decoder.</p>
For BiLSTM encoders with multiple layers, we combine the states for each layer to create a tuple of <code>LSTMStateTuple</code> objects. The element at index $i$ of the tuple is the $i^{th}$ layer's combined final state.


<h2>Chapter Goals:</h2>
<ul>
	<li>Combine the final states for each BiLSTM layer</li>
</ul>


<h2>A. LSTMStateTuple initialization</h2>

<div id="section1_l3">
<p>We initialize an <code>LSTMStateTuple</code> object with a hidden state (<code>c</code>) and state output (<code>h</code>).</p>
<p>Below we show an example of initializing an <code>LSTMStateTuple</code> object using the final forward and backward states from a single layer BiLSTM encoder.</p>

Combine the final states for a BiLSTM into usable initial states.

What you'll learn from this course

Word Embeddings

Language Model

Text Classification

Seq2Seq Model

Combined State

Chapter Goals:

A. LSTMStateTuple initialization