We may earn an affiliate commission when you visit our partners.
Course image
Giuseppe Gullo and Profession AI

Il Natural Language Processing è il cuore di Google Search e Google Translate ed è la tecnologia che da la voce a Siri, Alexa, Google Assistant e tutti gli altri assistenti virtuali

Read more

Il Natural Language Processing è il cuore di Google Search e Google Translate ed è la tecnologia che da la voce a Siri, Alexa, Google Assistant e tutti gli altri assistenti virtuali

In questo corso apprenderemo i segreti Natural Language Processing e impareremo ad utilizzarlo su problemi reali come:

  • Eseguire l'analisi del sentiment su recensioni di film usando scikit-learn

  • Raggruppare automaticamente articoli di giornale in base all'argomento usando Gensim

  • Creare un Chatbot per la customer care usando Keras e Tensorflow

  • Generare del nuovo testo in stile Dante Alighieri usando le Reti Neurali Ricorrenti con Keras e Tensorflow.

Nella prima sezione del corso vedremo come estrarre il testo da diverse tipologie di file come file

Vedremo in sintesi il funzionamento delle espressioni regolari e come possiamo sfruttarle nel Natural Language Processing.

La terza sezione è interamente dedicata alle tecniche di preprocessing del corso: estrazione dei tokens, rimozione dello stopwords e stemming e lemmatizzazione, che ci permettono di ottenere la radice di una parola in modo da ridurre la dimensione del nostro dizionario, in questa sezione useremo le due più popolari librerie Python per il Natural Language Processing:

  • NLTK (Natural Language Toolkit): storica libreria Python con moltissime funzioni.

  • Spacy: una libreria più recente sviluppata per essere utilizzata a livello industriale.

Continueremo il corso con i due principali modelli per l'encoding di documenti di testo, il modello Bag of Words e il TF*IDF, impareremo ad implementarli da zero, usando soltanto Numpy, una libreria Python per il calcolo scientifico.

Nella quinta sezione osserveremo come eseguire l'analisi del testo di un documento di testo usando sempre NLTK e Spacy, evidenziando:

  • La parte del discorso (Part of Speech Tagging)

  • Il tipo di entità (Named Entity Recognition)

Nella quinta sezione introdurremmo la sentiment analysis e parleremo di machine learning, il campo dell'intelligenza artificiale che ha rivoluzionato l'intero settore. Vedremo come estrarre il sentiment da un elenco di recensioni reali di una skill Alexa usando il modello VADER ed impareremo a preprocessare da zero l'IMDB Movie Reviews Dataset per poi eseguire la sentiment analysis creando un modello di regressione logistica con scikit-learn, la più popolare libreria python per il machine learning, e un modello bayesiano usando NLTK.

La sesta sezione è dedicata al Topic Modelling, dopo aver introdotto l'argomento insieme all'algoritmo Latent Dirichlet Allocation svolgeremo due esericizi:

  • Sfrutteremo un dataset con circa 9000 articoli del New York Times per estrarre i topic e raggruppare insieme articoli che trattano di un'argomento comune, a questo scopo implementeremo l'algoritmo  Latent Dirichlet Allocation usando scikit-learn.

  • Eseguiremo il Topic Modelling usando un dataset di un milione di titoli di giornale dell'ABC, usando sempre l'algoritmo  Latent Dirichlet Allocation ma questa volta con Gensim, una libreria Python specifica per il Topic Modelling.

Nella sezione che segue ci butteremo su Deep Learning e Reti Neurali Artificiali, studiando come queste funzionano e come possono essere applicate per la creazione di un Chatbot per l'assistenza clienti di un fantomatico operatore telefonico chiamato Miao Mobile, usando i due più popolari framework Python per il deep learning: Keras e Tensorflow.

Nell'ultima sezione parleremo di Reti Neurali Ricorrenti e di come vengono applicate a problemi di NLP, vedremo insieme le principali architetture: 

  • Vanilla RNN

  • Long short-term memory (LSTM)

  • Gated Recurrent Unit (GRU)

Come esercizio pratico utilizzeremo l'architettura LSTM per generare nuove testo con lo stile di scrittura di Dante Alighieri, usando come corpus di testo l'intera Divina Commedia.

Concluderemo il corso con una serie di consigli, letture ed esercizi per poter continuare la nostra avventura nel Natural Language Processing.

Enroll now

What's inside

Syllabus

Introduzione
Introduzione al Natural Language Processing
Come usare Google Colaboratory
Prima di cominciare
Read more
Domande Frequenti
Estrazione del testo
Operare sulle stringhe con Python
Estrarre testo da file TXT
Estrarre testo da file PDF
Estrarre testo da file Docx
Estrarre testo da file HTML
Estrarre testo da pagine Web
Estrarre testo da file CSV
Approfondimenti e riferimenti
Le Espressioni Regolari
Introduzione alle Espressioni Regolari
Espressioni regolari per cercare pattern in Python
Espressioni regolari per cercare pattern multipli in Python
Espressioni regolari per rimuovere pattern in Python
Preprocessing del testo
La Tokenizzazione
Tokenizzazione con Python e NLTK
Le Stop Words
Rimozione delle Stop Words con Python e NLTK
Lo Stemming
Stemming in Python e NLTK con il Porter Stemmer
Stemming in Python e NLTK con lo Snowball Stemmer
Stemming in Python e NLTK con il Lancaster Stemmer
La Lemmatizzazione
Lemmatizzazione con Python e NLTK
Introduzione a Spacy
Preprocessing di testo inglese con Spacy
Preprocessing di testo italiano con Spacy
Codifica del testo
Il modello Bag of Words
Bag of Words con Python e Numpy
Il modello TF*IDF
TF*IDF con Python e Numpy
Analisi del Testo
Part of Speech Tagging
POS con Python e NLTK
POS con Python e Spacy
Named Entity Recognition
NER con Spacy di un documento inglese
NER con Spacy di un documento italiano
Correzione delle entità
Visualizzare le entità con Displacy
Analisi del Sentiment
Introduzione alla Sentiment Analysis
Usare il modello VADER con NLTK
Analisi del sentiment di recensioni con NLTK
Introduzione al Machine Learning
[OPZIONALE] La Regressione Lineare e Logistica
[OPZIONALE] L'algoritmo Gradient Descent
Introduzione all'IMDB Movie Reviews Dataset
Preprocessing del corpus di testo
Regressione Logistica con scikit-learn
Correggere l'Overfitting con la regolarizzazione
Testiamo il modello su nuove recensioni
Preprocessing del corpus con NLTK
Classificatore Bayesiano con NLTK
Topic Modelling
Introduzione al Topic Modelling
Il modello Latent Dirichlet Allocation
Introduzione al New York Times Articles Dataset e alle API di Kaggle
Preprocessing del New York Times Articles Dataset
Creazione del modello LDA con scikit-learn
Esplorazione dei Topic
Testiamo il modello LDA su nuovi articoli
Rappresentazione grafica del modello LDA con scikit-learn
Introduzione e installazione di Gensim
Preprocessing dell'ABC Headlines Dataset con Gensim
Creazione del modello LDA con Gensim
Rappresentazione grafica del modello LDA con Gensim
Deep Learning e Chatbot
Introduzione al Deep Learning
[OPZIONALE] Funzionamento delle Reti Neurali Artificiali
[OPZIONALE] L'algoritmo Backpropagation
Installazione di Keras e Tensorflow
Preprocessare il corpus del Chatbot
Addestrare la Rete Neurale Artificiale
Creare il Chatbot
Word Embedding e Word2Vec
Limiti del Bag of Words
Introduzione al Word Embedding
Caricare l'IMDB Dataset con Keras
Preprocessare l'IMDB Dataset
Creare uno strato di Embedding
Ottenere i Word Vectors
Il modello Word2Vec
Importare il modello Word2Vec con Gensim
Introduzione al modello GloVe
Preparazione della matrice dei pesi

Good to know

Know what's good
, what to watch for
, and possible dealbreakers
Sviluppa competenze di base per i principianti
Rinforza le competenze esistenti per studenti di livello intermedio
Esamina l'analisi del sentiment, che è altamente rilevante nell'analisi del feedback dei clienti
Esplora il Topic Modelling, utile per organizzare grandi quantità di testo non strutturato
Studia le reti neurali ricorrenti, preziose per gestire dati sequenziali come il testo
Utilizza Keras e Tensorflow, due framework popolari per il deep learning

Save this course

Save Natural Language Processing con Python: il Corso Completo to your list so you can find it easily later:
Save

Activities

Be better prepared before your course. Deepen your understanding during and after it. Supplement your coursework and achieve mastery of the topics covered in Natural Language Processing con Python: il Corso Completo with these activities:
Review Python Basics
Review fundamental Python concepts to ensure a strong foundation for the course's technical requirements.
Browse courses on Python Programming
Show steps
  • Review data types, variables, and operators.
  • Practice control flow and looping.
  • Explore Python libraries for data analysis and machine learning.
Review Tokenization
Review basic tokenization in Python and NLTK to refresh foundational knowledge in text preprocessing.
Browse courses on Tokenization
Show steps
  • Read the NLTK documentation on tokenization.
  • Practice tokenizing text using NLTK's word_tokenize function.
  • Explore alternative tokenization methods, such as sentence tokenization and part-of-speech tagging.
NLP Tools and Resources Collection
Gather and organize NLP tools, libraries, and resources to enhance learning and facilitate future projects.
Show steps
  • Research and identify popular NLP tools and frameworks.
  • Create a repository or document to store and share the resources.
  • Categorize and annotate the resources for easy reference.
Five other activities
Expand to see all activities and additional details
Show all eight activities
Sentiment Analysis Exercises
Practice sentiment analysis techniques to strengthen understanding in classifying and analyzing text sentiment.
Browse courses on Sentiment Analysis
Show steps
  • Use the VADER model to analyze customer reviews.
  • Implement a logistic regression model for sentiment analysis.
  • Evaluate model performance and explore techniques for improving accuracy.
Connect with NLP Professionals
Connect with NLP professionals to gain insights, guidance, and potential collaboration opportunities.
Browse courses on Networking
Show steps
  • Attend industry events and conferences.
  • Join online NLP communities and forums.
  • Reach out to researchers and practitioners in the field.
Design a Chatbot Prototype
Design and prototype a chatbot to enhance practical understanding of building conversational AI systems.
Browse courses on Chatbot Development
Show steps
  • Define user personas and chatbot goals.
  • Create a chatbot knowledge base.
  • Train a deep learning model for natural language processing.
  • Develop a user interface for the chatbot.
  • Test and iterate on the chatbot prototype.
Participate in NLP Hackathons
Participate in NLP hackathons to apply skills, collaborate with others, and showcase projects.
Show steps
  • Find and register for NLP hackathons.
  • Form a team or collaborate with individuals.
  • Develop and present an NLP solution to a given problem.
Build an NLP Classification Model
Develop and deploy an NLP classification model to expand practical experience in applying machine learning techniques.
Browse courses on Classification Modeling
Show steps
  • Define the classification problem and collect data.
  • Preprocess and vectorize the text data.
  • Train and evaluate a machine learning model.
  • Deploy the model and measure its performance.

Career center

Learners who complete Natural Language Processing con Python: il Corso Completo will develop knowledge and skills that may be useful to these careers:
Language Scientist
A language scientist designs and applies natural language processing (NLP) solutions to real-world problems. This course can provide you with the foundational skills and knowledge you need to design and build NLP systems, from data preprocessing to model training and evaluation, which are in high demand in industries such as healthcare, finance, and technology.
Data Scientist
Data scientists use NLP to extract insights from unstructured text data. This course can help you build the skills and knowledge you need to succeed in this role, including data preprocessing, feature engineering, model training, and evaluation.
Machine Learning Engineer
Machine learning engineers build and deploy NLP models. This course can provide you with the foundational skills and knowledge you need to succeed in this role, including data preprocessing, model training, and evaluation.
Natural Language Processing Engineer
NLP engineers design and develop NLP systems. This course can provide you with the foundational skills and knowledge you need to succeed in this role, including data preprocessing, model training, and evaluation.
Computational Linguist
Computational linguists use NLP to understand the structure and meaning of language. This course can provide you with the foundational skills and knowledge you need to succeed in this role, including data preprocessing, model training, and evaluation.
Data Analyst
Data analysts use NLP to extract insights from unstructured text data. This course may be useful for data analysts who want to develop their skills in NLP.
Software Engineer
Software engineers use NLP to build and deploy NLP systems. This course may be useful for software engineers who want to develop their skills in NLP.
Product Manager
Product managers use NLP to understand the needs of users and develop products that meet those needs. This course may be useful for product managers who want to develop their skills in NLP.
Business Analyst
Business analysts use NLP to extract insights from unstructured text data. This course may be useful for business analysts who want to develop their skills in NLP.
Technical Writer
Technical writers use NLP to create user-friendly documentation. This course may be useful for technical writers who want to develop their skills in NLP.
Information Architect
Information architects use NLP to design and organize information systems. This course may be useful for information architects who want to develop their skills in NLP.
User Experience Designer
User experience designers use NLP to understand the needs of users and design products that meet those needs. This course may be useful for UX designers who want to develop their skills in NLP.
Content Strategist
Content strategists use NLP to create and manage content that meets the needs of users. This course may be useful for content strategist who want to develop their skills in NLP.
Marketing Manager
Marketing managers use NLP to understand the needs of customers and develop marketing campaigns that meet those needs. This course may be useful for marketing managers who want to develop their skills in NLP.
Customer Service Representative
Customer service representatives use NLP to provide customer support. This course may be useful for customer service representatives who want to develop their skills in NLP.

Reading list

We've selected 12 books that we think will supplement your learning. Use these to develop background knowledge, enrich your coursework, and gain a deeper understanding of the topics covered in Natural Language Processing con Python: il Corso Completo.
Comprehensive guide to deep learning for natural language processing. It covers a wide range of topics, from basic concepts to advanced techniques. This book valuable resource for anyone who wants to learn about deep learning for NLP.
Comprehensive guide to natural language understanding for question answering. It covers a wide range of topics, from basic concepts to advanced techniques. This book valuable resource for anyone who wants to learn about natural language understanding for question answering.
Comprehensive guide to natural language processing using Python. It covers a wide range of topics, from basic concepts to advanced techniques. This book valuable resource for anyone who wants to learn about NLP.
Practical guide to using TensorFlow for natural language processing. It covers a wide range of topics, from basic text processing to advanced machine learning techniques. This book valuable resource for anyone who wants to learn how to use TensorFlow for NLP.
Comprehensive guide to natural language processing with Python and NLTK. It covers a wide range of topics, from basic concepts to advanced techniques. This book valuable resource for anyone who wants to learn how to use NLTK for NLP.
Concise guide to natural language processing with Python. It covers the essential concepts of NLP, including text preprocessing, tokenization, stemming, lemmatization, and part-of-speech tagging. This book valuable resource for anyone who wants to learn the basics of NLP.
Provides an overview of text mining with R, a statistical programming language that is widely used for data analysis.
Provides an overview of deep learning for natural language processing, including topics such as word embeddings, recurrent neural networks, and attention mechanisms.
Comprehensive guide to deep learning for natural language processing. It covers a wide range of topics, from basic concepts to advanced techniques. This book valuable resource for anyone who wants to learn about deep learning for NLP.

Share

Help others find this course page by sharing it with your friends and followers:

Similar courses

Here are nine courses similar to Natural Language Processing con Python: il Corso Completo.
Big Data Analytics con Python e Spark 2.4: il Corso...
Most relevant
Python Pro - La Guida Completa, da Zero a Professionista
Most relevant
Corso completo per Data Science e machine learning con R
Most relevant
Impara l'Inglese - Livello B1
Most relevant
Python per la Data Science
Most relevant
La Pizza al Padellino/Tegamino e La Pata-Pizza senza...
Most relevant
Introduzione alla Data Visualization con Tableau
Most relevant
Encoder-Decoder Architecture - Italiano
Most relevant
Le politiche pubbliche come strategia di governo
Most relevant
Our mission

OpenCourser helps millions of learners each year. People visit us to learn workspace skills, ace their exams, and nurture their curiosity.

Our extensive catalog contains over 50,000 courses and twice as many books. Browse by search, by topic, or even by career interests. We'll match you to the right resources quickly.

Find this site helpful? Tell a friend about us.

Affiliate disclosure

We're supported by our community of learners. When you purchase or subscribe to courses and programs or purchase books, we may earn a commission from our partners.

Your purchases help us maintain our catalog and keep our servers humming without ads.

Thank you for supporting OpenCourser.

© 2016 - 2024 OpenCourser