Comprehensive theory presentations and practical programs for the Third Year Artificial Intelligence and Data Science course.
This course introduces students to the fundamental concepts of natural language processing and linguistic structures. It covers text preprocessing, corpus handling, and feature extraction techniques. Students will learn about statistical NLP techniques (like N-grams, HMMs, and parsing), implement tasks like POS tagging and NER, and explore modern neural NLP concepts including transformer architectures and BERT.
Download the unit-wise presentation slides used during the lectures.
Covers history of NLP, formal language concepts, context-free grammars, linguistic levels, edit distance, and Python-based NLP libraries.
Download PresentationCovers corpus types, text preprocessing (tokenization, stemming, etc.), word representation (sparse vs dense), and feature extraction (TF-IDF, Word2Vec).
Download PresentationCovers probability basics, N-gram language models, classification models (Naive Bayes, Logistic Regression), tagging models (HMMs), and probabilistic parsing.
Download PresentationCovers sequence labeling tasks (POS Tagging, NER), parsing (dependency vs constituency), evaluation metrics, core applications (sentiment analysis, retrieval), speech processing, and model deployment.
Download PresentationSr. Data Scientist, MITU Research, Pune
