Toll Free 1800-123-321-5

Natural Language Processing

This course covers a wide range of tasks in Natural Language Processing from basic to advanced, from sentiment analysis, and summarization to dialogue state tracking, among many other trending concepts. Upon completing the course learners will be able to recognize NLP tasks in their day-to-day work, propose approaches, and judge what techniques are likely to work efficiently. Learners will also demonstrate skills required to build conversational chat-bots, have an understanding of how to use the Natural Language Tool Kit, be able to load and manipulate your text data and know how to formulate solutions to text based problems
6 Days
06 May To 11May 2019
19:30 - 22:30 (Online)
INR 14999(Amount Exclusive of all taxes and 18% GST)
Enroll Now
Print Friendly, PDF & Email


Basics of Python Programming



Software to be installed –

Anaconda for python 3 – (According to bit version 32 bit for 32 Machine and 64 bit for 64 bit machine)

Machine Requirement:

Recommended – Machine with minimum 4GB RAM, i3 or above quadcore processor

Requirement: Working Internet Connection throughout the training for trainer as well as for participants.

Python Libraries used (Most of them are already available in Anaconda, others we will install during the training):

  • Numpy
  • Matplotlib
  • Pandas
  • Theano
  • Scikit-learn
  • TensorFlow
  • Seaborn
  • NLTK
  • TextBlob

Course Content

  • AI and NLP
  • Artificial Intelligence & Machine Learning Introduction
  • Supervised & Unsupervised Learning
  • Regression & Classification Problems
  • NLP Applications
  • Artificial Intelligence and NLP
  • Natural Language Understanding
  • Text Understanding
  • Semantic, Syntactic and Discourse Planning
  • Natural Language Generation
  • Getting started NLTK and Textblob
  • Using NLTK for NLP
  • Stemming and Lemmatization
  • POS Tagging
  • Text Vectorization
  • Frequency based Vectorization -Count Vectorizer, TF-IDF and Co occurrence Vectorization
  • Prediction based Embedding Techniques
  • Word2Vec, Fast Text and Glove
  • Topic Modelling
  • Unigram and Bigram Text Analysis
  • Conditional Probability and Bayes Theorem
  • Naïve Bayes Classifier
  • Email Classification using Naïve Bayes
  • Hierarchical Clustering
  • K Means Clustering
  • Use Cases for K Means Clustering
  • Programming for K Means using Python
  • Cluster Size Optimization vs Definition Optimization
  • Projects & Case Studies
  • Sentiment Analysis
  • Building Text Classification Model using Naïve Bayes
  • Using Twittter API
  • Project: Fetching live tweets from twitter and doing sentiment analysis using textblob
  • Chat bot Development
  • Project: Training a beta kernel for chatbot
  • Using Trained kernels
  • Project: Building chatbot using chatterbot API
  • Project: Building chatbot in indian local Language (Gujarati/Hindi/Tamil/Telugu/Bangla etc.)
  • Building Chatbot using other available API
  • Building Chatbot with Google DialogFlow and Facebook Messenger
  • Building chatbot with Chatfuel

Artificial Neural Networks with case study

  • Neurons, ANN & Working
  • Single Layer Perceptron Model
  • Multilayer Neural Network
  • Feed Forward Neural Network
  • Cost Function Formation
  • Applying Gradient Descent Algorithm
  • Use Cases of ANN
  • The Programming Model
  • Data Model, Tensor Board
  • Tensorflow – variables, placeholders and constants
  • Linear Regression using Tensorflow
  • Introducing Feed Forward Neural Nets
  • Basic concepts of RNN
  • Unfolding Recurrent Neural Networks
  • The Vanishing Gradient Problem
  • The Exploding Gradient Problem
  • LSTM Networks
  • Sentiment Analysis using LSTM
  • Text Analysis using LSTM
  • Sequence to Sequence models for Chatbots