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.
Ce cours fait partie de la Spécialisation TensorFlow in Practice
Natural Language Processing in TensorFlow
Offert par
À propos de ce cours
289,658 consultations récentes
Ce que vous allez apprendre
Build natural language processing systems using TensorFlow
Process text, including tokenization and representing sentences as vectors
Apply RNNs, GRUs, and LSTMs in TensorFlow
Train LSTMs on existing text to create original poetry and more
Compétences que vous acquerrez
Natural Language ProcessingTokenizationMachine LearningTensorflowRNNs
Certificat partageable
Obtenez un Certificat lorsque vous terminez
100 % en ligne
Commencez dès maintenant et apprenez aux horaires qui vous conviennent.
Cours 3 sur 4 dans le
Dates limites flexibles
Réinitialisez les dates limites selon votre disponibilité.
Niveau intermédiaire
You should take the first 2 courses of the TensorFlow Specialization and be comfortable coding in Python and understanding high school-level math.
Approx. 9 heures pour terminer
Recommandé : 4 weeks of study, 4-5 hours/week
Anglais
Sous-titres : Anglais, Coréen
Programme du cours : ce que vous apprendrez dans ce cours
3 heures pour terminer
Sentiment in text
The first step in understanding sentiment in text, and in particular when training a neural network to do so is the tokenization of that text. This is the process of converting the text into numeric values, with a number representing a word or a character. This week you'll learn about the Tokenizer and pad_sequences APIs in TensorFlow and how they can be used to prepare and encode text and sentences to get them ready for training neural networks!
3 heures pour terminer
13 vidéos (Total 30 min), 1 lecture, 3 quiz
13 vidéos
Introduction1 min
Word based encodings2 min
Using APIs2 min
Notebook for lesson 12 min
Text to sequence3 min
Looking more at the Tokenizer1 min
Padding2 min
Notebook for lesson 24 min
Sarcasm, really?2 min
Working with the Tokenizer1 min
Notebook for lesson 33 min
Week 1 Wrap up21s
1 lecture
News headlines dataset for sarcasm detection10 min
1 exercice pour s'entraîner
Week 1 Quiz
3 heures pour terminer
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.
3 heures pour terminer
14 vidéos (Total 39 min), 5 lectures, 3 quiz
14 vidéos
Introduction2 min
The IMBD dataset1 min
Looking into the details4 min
How can we use vectors?2 min
More into the details2 min
Notebook for lesson 110 min
Remember the sarcasm dataset?1 min
Building a classifier for the sarcasm dataset1 min
Let’s talk about the loss function1 min
Pre-tokenized datasets43s
Diving into the code (part 1)1 min
Diving into the code (part 2)2 min
Notebook for lesson 35 min
5 lectures
IMDB reviews dataset10 min
Try it yourself10 min
TensoFlow datasets10 min
Subwords text encoder10 min
Week 2 Wrap up10 min
1 exercice pour s'entraîner
Week 2 Quiz
3 heures pour terminer
Sequence models
In the last couple of weeks you looked first at Tokenizing words to get numeric values from them, and then using Embeddings to group words of similar meaning depending on how they were labelled. This gave you a good, but rough, sentiment analysis -- words such as 'fun' and 'entertaining' might show up in a positive movie review, and 'boring' and 'dull' might show up in a negative one. But sentiment can also be determined by the sequence in which words appear. For example, you could have 'not fun', which of course is the opposite of 'fun'. This week you'll start digging into a variety of model formats that are used in training models to understand context in sequence!
3 heures pour terminer
10 vidéos (Total 16 min), 4 lectures, 3 quiz
10 vidéos
Introduction2 min
LSTMs2 min
Implementing LSTMs in code1 min
Accuracy and loss1 min
A word from Laurence35s
Looking into the code1 min
Using a convolutional network1 min
Going back to the IMDB dataset1 min
Tips from Laurence37s
4 lectures
Link to Andrew's sequence modeling course10 min
More info on LSTMs10 min
Exploring different sequence models10 min
Week 3 Wrap up10 min
1 exercice pour s'entraîner
Week 3 Quiz
3 heures pour terminer
Sequence models and literature
Taking everything that you've learned in training a neural network based on NLP, we thought it might be a bit of fun to turn the tables away from classification and use your knowledge for prediction. Given a body of words, you could conceivably predict the word most likely to follow a given word or phrase, and once you've done that, to do it again, and again. With that in mind, this week you'll build a poetry generator. It's trained with the lyrics from traditional Irish songs, and can be used to produce beautiful-sounding verse of it's own!
3 heures pour terminer
14 vidéos (Total 27 min), 3 lectures, 3 quiz
14 vidéos
Introduction1 min
Looking into the code57s
Training the data2 min
More on training the data1 min
Notebook for lesson 18 min
Finding what the next word should be2 min
Example1 min
Predicting a word1 min
Poetry!40s
Looking into the code1 min
Laurence the poet!1 min
Your next task1 min
A conversation with Andrew Ng1 min
3 lectures
link to Laurence's poetry10 min
Link to generating text using a character-based RNN10 min
Wrap up10 min
1 exercice pour s'entraîner
Week 4 Quiz
Avis
4.6
Meilleurs avis pour NATURAL LANGUAGE PROCESSING IN TENSORFLOW
par GSAug 26, 2019
Excellent. Isn't Laurence just great! Fantastically deep knowledge, easy learning style, very practical presentation. And funny! A pure joy, highly relevant and extremely useful of course. Thank you!
par DWNov 19, 2019
These classes are excelling practical examples of how to use tensorflow for various problem types. My only objection is they are slightly light on the actual, behind the scenes, math and intuition.
par MUFeb 28, 2020
Excellent course\n\nGave me a brief idea with practical experience about how to process strings for machine learning.\n\nI would like to thank Laurence Sir\n\nand a Special thanks to Andrew Sir
par SBAug 18, 2019
Good course that gives you basic understanding of word embeddings, sequence analysis, and many other things. Thank you for Mr. Moroney and the entire Coursera team for making it available.
par AMSep 22, 2019
Excellent course. Teaches NLP thoroughly, going from the basics such as tokenization and padding to complex topics such as word embeddings and sequence models (like RNNs, LSTMs and GRUs).
par CLAug 4, 2019
Great course with fun examples! Probably more valuable after completing Deep Learning Specialization/Sequence Models by Andrew Ng (https://www.coursera.org/learn/nlp-sequence-models)
par ADec 29, 2019
This is good course for those who are want to practice in natural language processing in Tensor Flow and also learned sentiment analysis it is having wonderful stuff for beginners
par ADec 18, 2019
Excellent course. Teaches NLP thoroughly, going from the basics such as tokenization and padding to complex topics such as word embeddings and sequence models (like RNNs, LSTMs)
Offert par
deeplearning.ai
deeplearning.ai is Andrew Ng's new venture which amongst others, strives for providing comprehensive AI education beyond borders.
À propos du Spécialisation TensorFlow in Practice
Discover the tools software developers use to build scalable AI-powered algorithms in TensorFlow, a popular open-source machine learning framework.
In this four-course Specialization, you’ll explore exciting opportunities for AI applications. Begin by developing an understanding of how to build and train neural networks. Improve a network’s performance using convolutions as you train it to identify real-world images. You’ll teach machines to understand, analyze, and respond to human speech with natural language processing systems. Learn to process text, represent sentences as vectors, and input data to a neural network. You’ll even train an AI to create original poetry!
AI is already transforming industries across the world. After finishing this Specialization, you’ll be able to apply your new TensorFlow skills to a wide range of problems and projects.
Looking for more advanced TensorFlow content? Check out the new TensorFlow: Data and Deployment Specialization.
Foire Aux Questions
Quand aurai-je accès aux vidéos de cours et aux devoirs ?
Une fois que vous êtes inscrit(e) pour un Certificat, vous pouvez accéder à toutes les vidéos de cours, et à tous les quiz et exercices de programmation (le cas échéant). Vous pouvez soumettre des devoirs à examiner par vos pairs et en examiner vous-même uniquement après le début de votre session. Si vous préférez explorer le cours sans l'acheter, vous ne serez peut-être pas en mesure d'accéder à certains devoirs.
À quoi ai-je droit si je m'abonne à cette Spécialisation ?
Lorsque vous vous inscrivez au cours, vous bénéficiez d'un accès à tous les cours de la Spécialisation, et vous obtenez un Certificat lorsque vous avez réussi. Votre Certificat électronique est alors ajouté à votre page Accomplissements. À partir de cette page, vous pouvez imprimer votre Certificat ou l'ajouter à votre profil LinkedIn. Si vous souhaitez seulement lire et visualiser le contenu du cours, vous pouvez accéder gratuitement au cours en tant qu'auditeur libre.
Quelle est la politique de remboursement ?
Une aide financière est-elle possible ?
D'autres questions ? Visitez le Centre d'Aide pour les Etudiants.