Book Image

fastText Quick Start Guide

By : Joydeep Bhattacharjee
Book Image

fastText Quick Start Guide

By: Joydeep Bhattacharjee

Overview of this book

Facebook's fastText library handles text representation and classification, used for Natural Language Processing (NLP). Most organizations have to deal with enormous amounts of text data on a daily basis, and gaining efficient data insights requires powerful NLP tools such as fastText.  This book is your ideal introduction to fastText. You will learn how to create fastText models from the command line, without the need for complicated code. You will explore the algorithms that fastText is built on and how to use them for word representation and text classification.  Next, you will use fastText in conjunction with other popular libraries and frameworks such as Keras, TensorFlow, and PyTorch.  Finally, you will deploy fastText models to mobile devices. By the end of this book, you will have all the required knowledge to use fastText in your own applications at work or in projects.

Related Content you might be interested in

Current Title:

Small book image
fastText Quick Start Guide
Joydeep Bhattacharjee
Jul, 2018 | 194 pages
Small book image
Hands-On Python Natural Language Processing
Mayank Rasu | Aman Kedia
Jun, 2020 | 316 pages
Small book image
Natural Language Processing and Computational Linguistics
Bhargav SrinivasaDesikan
Jun, 2018 | 306 pages
Small book image
Natural Language Processing with Python Quick Start Guide
Nirant Kasliwal
Nov, 2018 | 182 pages
Table of Contents (14 chapters)
Preface
Preface
Who this book is for
What this book covers
To get the most out of this book
Get in touch
Free Chapter
1
First Steps
First Steps
2
Introducing FastText
Introducing FastText
Introducing fastText
Installing fastText
Installing dependencies on Mac systems
Installing Python dependencies
Using a Docker image for fastText
Summary
3
Creating Models Using FastText Command Line
Creating Models Using FastText Command Line
Text classification using fastText
FastText word vectors
Summary
4
The FastText Model
The FastText Model
5
Word Representations in FastText
Word Representations in FastText
Word-to-vector representations
Summary
6
Sentence Classification in FastText
Sentence Classification in FastText
Sentence classification
fastText supervised learning
fastText model quantization
Summary
7
Using FastText in Your Own Models
Using FastText in Your Own Models
8
FastText in Python
FastText in Python
FastText official bindings
Gensim
Summary
9
Machine Learning and Deep Learning Models
Machine Learning and Deep Learning Models
Scikit-learn and fastText
Embeddings
Keras
TensorFlow
PyTorch
Summary
10
Deploying Models to Web and Mobile
Deploying Models to Web and Mobile
Deploying to the web
Deploying to smaller devices
Summary
11
Notes for the Readers
Notes for the Readers
Windows and Linux
Python 2 and Python 3
The fastText command line
Gensim fastText parameters
12
References
References
Chapter 3
Chapter 4
Chapter 5
Chapter 6
Chapter 7
13
Other Books You May Enjoy
Other Books You May Enjoy
Leave a review - let other readers know what you think

Keras

Keras is a widely popular high-level neural network API. It supports TensorFlow, CNTK, and Theano as the backend. Due to the user-friendly API of Keras, many people use it in lieu of the base libraries.

Embedding layer in Keras

The embedding layer will be the first hidden layer of the Keras network and you will need to specify three arguments: input dimension, output dimension, and input length. Since we will be using fastText to make our model better, we will also need to pass the weights parameter with the embedding matrix and make the trainable matrix to be false:

embedding_layer = Embedding(num_words,
                            EMBEDDING_DIM, 
                            weights=[embedding_matrix],
               ...
Previous Section
End of Section 4
Next Section