Applied Machine Learning with NLP (10 op)

Tavoitteet

• Learn the basic concepts of NLP and its applications
• Learn various text preprocessing techniques like stemming, lemmatization, tokenizing
• Learn how to analyze a text
• Learn how to embed words
• Get familiar with text vectorization techniques
• Learn how to find the most used words in a text using wordcloud maps
• Learn how to create a simple recommender system
• Learn how to create a simple chatbot
• Gain hands-on experience performing sentiment analysis
• Learn how to classify texts
• Get familiar with machine learning models useful for NLP
• Gain hands-on experience training LSTM models
• Get familiar with deep learning and Keras
• Get acquainted with NLP libraries such as Gensim, NLTK, TextBlob, SpaCy
• Learn how to perform sentiment analysis with LSTM

Sisältö

1. Beginning with This Course
Our Approach in This Course- About TechClass AI Department- Your Expectations, Goals, and Knowledge

2. Introduction
What is NLP?- Why Should We Learn NLP?- Applications of Natural Language Processing- Python Libraries for NLP Problems- A General Overview of this course

3. Text Preprocessing Techniques
Introduction- Lower Case- Tokenization-Remove Unnecessary Elements- Stemming and Lemmatization-Numtowords- Pos tagging

4. Text Analysis
Introduction- Preprocessing- Length Analysis- Word Cloud - Sentiment Analysis- Topic Modeling

5. Language Model
Introduction- What is Language Model?- Text and Sentences Probability- N-Garm and LMS- N-Garm and LMS: Implementation- Neural Language Models- Named Entity Recognition

6. Text Vectorization Techniques
Introduction-One-Hot- Bag of Words- TF-IDF- Similarity Measures- Build Movie Recommender System: EDA- Build Movie Recommender System- Mini project: ChatBot

7. Word Embedding
Introduction- What is Word Embedding?- Count-Based Approach- Count-Based Methods- Word2Vec: Continuous Bag of Words (CBOW)- Word2Vec: Skip-Gram- Word2Vec for Your Corpus- GloVe- Word Embedding for News Category Dataset- Document Embedding

8. Classical Models for Text Classification
Introduction- Best Classical Models for Text Classification- Classification Evaluation Metrics: Review- Naïve Bayes- SVM- Maximum Entropy- Classification of News Category Dataset- Mini project

9. Deep Learning Overview
Introduction- What is Deep learning?- Deep Learning Architectures- What is Keras?- Overfitting- Regularization

10. LSTM for Text Classification
Introduction- Recurrent Neural Networks- How Does LSTM Work?- Why LSTM?- Implementing LSTM Using TensorFlow- Sentiment Analysis Using LSTM: Preprocessing- Sentiment Analysis using LSTM: Model Training- Building Simple Text Generator -Mini project

11. Final Tasks
Self-Study Essay

Aika ja paikka

Course can be done in own pace in TechClass portal.

Oppimateriaalit

Lecture slides, tutorial videos, quizzes, exercises and project can be find via TechClass portal.

Opetusmenetelmät

This course is 100% virtual thanks to the comprehensive tutorial videos and content prepared for this course.

The student will pass this course after submitting the required quiz, assignments, and the final project.

Harjoittelu- ja työelämäyhteistyö

N/A

Tenttien ajankohdat ja uusintamahdollisuudet

Online.

Kansainvälisyys

N/A

Toteutuksen valinnaiset suoritustavat

N/A

Opiskelijan ajankäyttö ja kuormitus

- Tutorial Videos
- Exercises
- Quiz
- Project
- Self-study

Sisällön jaksotus

Up to student her-/himself.

Arviointiasteikko

Hyväksytty/Hylätty

Arviointikriteeri, hyväksytty/hylätty

Exercises 40%
Quizzes 10%
Project 50%

Arviointimenetelmät ja arvioinnin perusteet

Exercises 40%
Quizzes 10%
Project 50%

Esitietovaatimukset

Introduction to Python for Data Science