Modules of the Workshop : Day - 1

Module – 1 : Introduction to NLP

Concepts Covered :

Overview of NLP, its goals, and applications. Discussion on the importance of NLP in real-world scenarios. Activity: Identify NLP applications in day-to-day life.

Learning Outcomes :

Understand the basics of NLP and its impact on various domains.

Module – 2 : Counting and Empirical Laws

Concepts Covered :

Introduction to Zipf’s and Heap’s law in text data. Hands-on: Calculate word frequency and visualize empirical relationships using Python.

Learning Outcomes :

Learn how text data follows empirical laws and analyze word frequency distributions.

Module – 3 : Word Representation Using a Vector

Concepts Covered :

Overview of word representation techniques (e.g., one-hot encoding, TF-IDF, embeddings). Hands-on: Implement TF-IDF on a small dataset.

Learning Outcomes :

Gain knowledge of vector-based word representation techniques and their applications.

Module – 4 : Feature Extraction Using n-Grams

Concepts Covered :

Introduction to n-grams and their role in capturing contextual information. Hands-on: Generate and analyze n-gram features using Python.

Learning Outcomes :

Learn to extract features from text data using n-grams and understand their importance in NLP tasks.

Module – 5 : Finding Word Vectors: Artificial Neural Network Approach

Concepts Covered :

Basics of word2vec (CBOW and skip-gram models). Hands-on: Train a word2vec model using Gensim or TensorFlow.

Learning Outcomes :

Understand and implement neural-based word vectorization methods like word2vec.

Module – 6 : Language Generation

Concepts Covered :

Basics of text generation using probabilistic models. Demo: Generate text using n-gram-based methods.

Learning Outcomes :

Explore the concept of generating coherent text using probabilistic language models.

Modules of the Workshop : Day - 2

Module – 1 : Probabilistic Language Models Using N-Grams

Concepts Covered :

Introduction to n-gram language models, smoothing techniques, and their limitations. Hands-on: Implement an n-gram-based language model in Python.

Learning Outcomes :

Understand probabilistic approaches to language modeling and their application in text prediction.

Module – 2 : Introduction to Neural Language Models

Concepts Covered :

Basics of feedforward neural networks and RNNs in NLP. Comparison between probabilistic and neural models.

Learning Outcomes :

Learn the foundational concepts of neural models for language tasks.

Module – 3 : Language Translation

Concepts Covered :

Introduction to sequence-to-sequence models and their application in translation.

Learning Outcomes :

Learn about the mechanisms of language translation using neural.

Module – 4 : Transformers

Concepts Covered :

Introduction to the Transformer architecture and its significance.

Learning Outcomes :

Understand the architecture and applications of Transformer models.

Module – 5 : Named Entity Recognition (NER)

Concepts Covered :

Basics of extracting named entities from text (e.g., names, dates).Hands-on: Implement NER using NLTK or a pretrained model.

Learning Outcomes :

Understand the fundamentals of entity extraction and apply them to real-world datasets. 

Module – 6 : Spam Detection

Concepts Covered :

Introduction to Bayesian classification for spam detection. Hands-on: Build and evaluate a Naive Bayes spam classifier using a dataset.

Learning Outcomes :

Learn to design and implement a probabilistic text classification system for spam detection.

Module – 7 : Introduction to Chatbots

Concepts Covered :

Overview of conversational AI and chatbot systems. Discussion on rule-based vs. AI-powered chatbots.

Learning Outcomes :

Understand the principles of conversational AI and basic chatbot implementation.

Module – 8 : Discussion and Future Directions

Concepts Covered :

Discuss recent advancements like GPT and BERT, ethics in NLP, and potential career opportunities. Interactive Q&A session.

Learning Outcomes :

Gain insight into cutting-edge NLP advancements and future trends.