Explore
For Enterprise
Join for Free
Log In

Artes e Humanas
Negócios
Ciência da Computação
Ciência de Dados
Tecnologia da informação
da saúdesaúde
Matemática e Lógica
Desenvolvimento Pessoal
Ciência e Engenharia Física
Ciências Sociais
Línguas
Notas
Certificados

Explore todo o Coursera

Navegar
Pesquisar
For Enterprise
Entrar
Inscreva-se gratuitamente

More into the details

Loading...

Natural Language Processing in TensorFlow

deeplearning.ai

4.6 (524 classificações) | 9.6K alunos inscritos

Curso 3 de 4 no TensorFlow in Practice Programa de cursos integrados

If you are a software developer who wants to build scalable AI-powered algorithms, you need to understand how to use the tools to build them. This Specialization will teach you best practices for using TensorFlow, a popular open-source framework for machine learning. In Course 3 of the deeplearning.ai TensorFlow Specialization, you will build natural language processing systems using TensorFlow. You will learn to process text, including tokenizing and representing sentences as vectors, so that they can be input to a neural network. You’ll also learn to apply RNNs, GRUs, and LSTMs in TensorFlow. Finally, you’ll get to train an LSTM on existing text to create original poetry! The Machine Learning course and Deep Learning Specialization from Andrew Ng teach the most important and foundational principles of Machine Learning and Deep Learning. This new deeplearning.ai TensorFlow Specialization teaches you how to use TensorFlow to implement those principles so that you can start building and applying scalable models to real-world problems. To develop a deeper understanding of how neural networks work, we recommend that you take the Deep Learning Specialization.

Visualizar o programa do curso

Habilidades que você aprenderá

Natural Language Processing, Tokenization, Machine Learning, Tensorflow, RNNs

Avaliações

4.6 (524 classificações)

5 stars
374 ratings
4 stars
110 ratings
3 stars
26 ratings
2 stars
9 ratings
1 star
5 ratings

GI

Jun 22, 2019

Amazing course by Laurence Moroney. But only after finishing Sequence Models by Andrew NG, I was able to understand the concepts taught here.

SM

Aug 15, 2019

Course explains some of key concept very well, like sequence model to predict next word using existing corpus.

Na lição

Word Embeddings

Last week you saw how to use the Tokenizer to prepare your text to be used by a neural network by converting words into numeric tokens, and sequencing sentences from these tokens. This week you'll learn about Embeddings, where these tokens are mapped as vectors in a high dimension space. With Embeddings and labelled examples, these vectors can then be tuned so that words with similar meaning will have a similar direction in the vector space. This will begin the process of training a neural network to udnerstand sentiment in text -- and you'll begin by looking at movie reviews, training a neural network on texts that are labelled 'positive' or 'negative' and determining which words in a sentence drive those meanings.

A conversation with Andrew Ng2:08

Introduction2:14

The IMBD dataset1:03

Looking into the details4:01

How can we use vectors?2:30

More into the details2:47

Notebook for lesson 110:09

Remember the sarcasm dataset?1:07

Building a classifier for the sarcasm dataset1:55

Let’s talk about the loss function1:26

Pre-tokenized datasets0:43

Diving into the code (part 1)1:25

Diving into the code (part 2)2:30

Notebook for lesson 35:10

Ministrado por

Laurence Moroney
AI Advocate

Transcrição

You can compile your model as before,

and print out the summary with this code.

Now training is the simplest passing

padded and your training labels

final as your training set,

specifying the number of epochs,

and passing the testing

padded and testing labels final as your test set.

Here's the results of training,

with the training set giving us 1.00

accuracy and the validation set at 0.8259.

So there's a good chance that we're overfitting.

We'll look at some strategies to avoid this later,

but you should expect results a little bit like this.

Okay. Now we need to talk

about and demonstrate the embeddings,

so you can visualize them like you

did right back at the beginning of this lesson.

We'll start by getting the results

of the embeddings layer,

which is layer zero.

We can get the weights,

and print out their shape like this.

We can see that this is a 10,000 by 16 array,

we have 10,000 words in our corpus,

and we're working in a 16 dimensional array,

so our embedding will have that shape.

To be able to plot it,

we need a helper function to reverse our word index.

As it currently stands,

our word index has the key being the word,

and the value being the token for the word.

We'll need to flip this around,

to look through the padded list to

decode the tokens back into the words,

so we've written this helper function.

Now it's time to write the vectors and

their metadata auto files.

The TensorFlow Projector reads this file type and

uses it to plot the vectors in

3D space so we can visualize them.

To the vectors file,

we simply write out the value of each

of the items in the array of embeddings,

i.e, the co-efficient of

each dimension on the vector for this word.

To the metadata array,

we just write out the words.

If you're working in Colab,

this code will download the two files.

To now render the results,

go to the TensorFlow Embedding Projector

on projector.tensorflow.org,

press the ''Load data'' button on the left.

You'll see a dialog asking

you to load data from your computer.

Use vector.TSV for the first one,

and meta.TSV for the second.

Once they're loaded, you should see something like this.

Click this ''sphereize data'' checkbox on the top left,

and you'll see the binary clustering of the data.

Experiment by searching for words,

or clicking on the blue dots in

the chart that represent words.

Above all, have some fun with it.

Next up, we'll step through

a screencast of what you've just seen,

so you can explore it in action.

After that, you'll look at how TFTS has built in

tokenizers that prevent you from

writing a lot of the tokenizing

code that we've just used.

Explore nosso catálogo

Registre-se gratuitamente e obtenha recomendações, atualizações e ofertas personalizadas.

O Coursera proporciona acesso universal à melhor educação do mundo fazendo parcerias com as melhores universidades e organizações para oferecer cursos on-line.

© 2019 Coursera Inc. Todos os direitos reservados.

Baixar na App Store

Baixar no Google Play

Coursera
Sobre
Liderança
Carreiras
Lista de cursos
Certificados
Certificados MasterTrack™
Notas
For Enterprise
For Government

Comunidade
Learners
Partners
Developers
Beta Testers
Translators

Conectar
Blog
Facebook
LinkedIn
Twitter
Instagram
YouTube
Tech Blog

Mais
Termos
Privacidade
Ajuda
Acessibilidade
Imprensa
Contato
Diretório
Afiliados