Data Science Specialization – NLP
(18 weeks of Learning)
After Completion of this Course, You’ll be Skilled to Apply For:
Job Description – NLP Engineer/ Text Mining
Primary Domain – E-Commerce/ Banking, financial services and insurance (BFSI)/ Telecom/ Pharma/ ITeS
Course Content
After the completion of 22 Modules of Level 1 & Level 2, you are just 7 weeks away from becoming a “Data Scientist”.
Module 23: Introduction to NLP
Module 24: Basic Techniques and Terminologies
- Types Of Models Language Model, Seq2Seq….
- Feature extraction from text
- Counting Text
- Frequency Distribution
- Conditional Frequency Distribution
Module 25: Python: Stemming, Tokenization, Lemmatization
- Counting Text
- NLTK basic
- Tokenization
- Normalization
- Lemmatization
Module 26: Text Classification Techniques
- Text Feature Extraction using Count Vectorizer, TF-IDF
- Classification techniques using features
- Linear models for sentiment analysis
- Hashing trick in spam filtering
- Introduction to Vector Space Models
- Word Vectors
- Skip Gram and CBOW
- Implementation using gensim
Module 31: Topic Modelling
- Semantic Text Similarity
- Topic Modeling
- Generative Models and LDA
- Information Extraction
Module 32: Python: Feature extraction and topic model representation
- LDA implementation using gensim
- Text Similarity
- LSA implemntation and comparison with LDA
Module 33: Introduction to Deep Learning
- What is Deep Learning?
- Network Architectures
- Gradient Descent
- Backpropagation
- Optimization Techniques
- Hyper-Parameter Tuning
Module 35: Recurrent Neural Networks, GRU
- Text NN Architectures
- LSTM (Long Short Term Memory)
- Vanishing Gradient
- Gated Recurrent Unit
Module 36: Python: RNN implementation using Keras
- Word Suggester
- Question Answering
Module 37: Deep Learning Case Study 1
Module 38: Deep Learning Case Study 2
