Modern Natural Language Processing in Python

Name: Modern Natural Language Processing in Python
Rating: 4.5 (1957 reviews)

Solve Seq2Seq and Classification NLP tasks with Transformer and CNN using Tensorflow 2 in Google Colab

Created byMartin Jocqueviel, SuperDataScience Team, Ligency

Last updated 6/2024

English

What you'll learn

Build a Transformer, new model created by Google, for any sequence to sequence task (e.g. a translator)
Build a CNN specialized in NLP for any classification task (e.g. sentimental analysis)
Write a custom training process for more advanced training methods in NLP
Create customs layers and models in TF 2.0 for specific NLP tasks
Use Google Colab and Tensorflow 2.0 for your AI implementations
Pick the best model for each NLP task
Understand how we get computers to give meaning to the human language
Create datasets for AI from those data
Clean text data
Understand why and how each of those models work
Understand everything about the attention mechanism, lying behind the newest and most powerful NLP algorithms

Course content

5 sections • 38 lectures • 5h 46m total length

Welcome! NLP introduction & course overview5:54
Course curriculum, Colab toolkit and data links0:28
EXTRA: Learning Path0:35

Introduction3:28
Old fashioned11:03
General understanding14:21
Learn how the transformer replaces RNNs by using self-attention to encode and decode whole sequences. Understand the encoder-decoder architecture and how attention enables global information flow across the input.
Attention31:25
Explore how the attention mechanism computes relations between sequence elements using dot products and softmax, then recombines them into representations. See how multi-head attention and lookahead masks enable transformer translation.
Positional encoding6:27
Explain how positional encoding inserts sine and cosine-based position signals into word embeddings to preserve word order in transformer encoders and decoders, addressing global attention limitations.
Last details8:12

Introduction4:25
Dependencies3:08
Loading Files4:42
Cleaning11:03
Tokenizing5:59
Max Length4:57
Inputs Creation4:16
Pad inputs and outputs to equal length with tf.keras.preprocessing.sequence.pad_sequences using zero padding and masking for attention. Then create shuffled, batched datasets with caching and prefetch for fast translator training.
Positional encoding11:30
Scaled dot product attention6:04
Multi head attention16:09
Encoder18:19
Learn to build a transformer encoder by embedding inputs, adding positional encoding, stacking encoder layers with multi-head attention, add and norm, and dense feedforward networks with dropout for training.
Decoder18:07
Transformer23:58
Training28:05
Evaluation13:47

Requirements

PC with Internet connection
Python Programming Skills
Recommended: Experience with TF2.0
Recommended: Google Collab

Description

Modern Natural Language Processing course is designed for anyone who wants to grow or start a new career and gain a strong background in NLP.

Nowadays, the industry is becoming more and more in need of NLP solutions. Chatbots and online automation, language modeling, event extraction, fraud detection on huge contracts are only a few examples of what is demanded today. Learning NLP is key to bring real solutions to the present and future needs.

Throughout this course, we will leverage the huge amount of speech and text data available online, and we will explore the main 3 and most powerful NLP applications, that will give you the power to successfully approach any real-world challenge.

First, we will dive into CNNs to create a sentimental analysis application.
Then we will go for Transformers, replacing RNNs, to create a language translation system.

The course is user-friendly and efficient: Modern NL leverages the latest technologies—Tensorflow 2.0 and Google Colab—assuring you that you won’t have any local machine/software version/compatibility issues and that you are using the most up-to-date tools.

Who this course is for:

AI amateurs that are eager to learn how we process language nowadays
AI students that need to have a deeper and wider knowledge about NLP
Business driven people that are eager to know how NLP can be applied to their field to leverage any text data
Anyone who wants to start a new career and get a strong background in NLP, adding efficient cases to their portfolio

Modern Natural Language Processing in Python

What you'll learn

Explore related topics

Course content

Introduction3 lectures • 7min

CNN for NLP - Intuition5 lectures • 34min

CNN for NLP - Application (sentimental analysis)9 lectures • 56min

Transformer - Intuition6 lectures • 1hr 15min

Transformer - Application15 lectures • 2hr 54min

Requirements

Description

Who this course is for: