Course

Unit 1

Introduction to Natural Language Processing (NLP), words, n-grams, language modelling, part-of-speech tagging, information extraction, named entity recognition, relation extraction, syntactic and semantic parsing, and morphological analysis. Introduction to NLP tools such as NLTK and spaCy for basic NLP tasks. Text representation and transformation including vector space models, Bag-of-Words, Term Frequency (TF), and Inverse Document Frequency (IDF).

Unit 3

Word vector representations including Word2Vec, GloVe, FastText, BERT, ALBERT, and RoBERTa. Word representations for Indic languages including IndicBERT, IndicFT, XLM, and MuRIL. Topic Modelling using Latent Dirichlet Allocation (LDA).

Unit 4

Neural language models including Recurrent Neural Networks (RNNs), Long Short-Term Memory (LSTM) Networks, encoder–decoder architecture, attention mechanism, and transformer networks. Large Language Models (LLMs), zero-shot learning, few-shot learning, and fine-tuning of LLMs. Applications including text classification, sentiment analysis, neural machine translation, question answering, and text summarization.

Course Objectives

• This course aims to provide an insight into the concepts of Natural Language Processing (NLP) and its applications.

• This course helps students implement NLP applications using deep learning algorithms.

• This course helps students understand various word/text representation algorithms.

Course Outcomes

After completing this course, the students will be able to,

• CO1: Apply word and text representation techniques to capture semantic relationships in textual data.

• CO2: Model natural language processing tasks using machine learning, deep learning, and large language models.

• CO3: Implement deep learning models for text mining and real-world text analytics applications.

• CO4: Evaluate natural language processing models using appropriate performance metrics and visualization techniques.

CO-PO Mapping

1. Daniel Jurafsky and James H. Martin, “Speech and Language Processing,” 3^rd edition, 2026. [Available on: https://web.stanford.edu/~jurafsky/slp3/ed3book_dec302020.pdf]

2. Christopher Manning and Hinrich Schutze, “Foundations of statistical natural language processing,” MIT press, 1999.

3. Jacob Eisenstein, “Introduction to natural language processing,” Illustrated edition, The MIT press, 2019.

4. Bengfort, Benjamin, Rebecca Bilbro, and Tony Ojeda. Applied text analysis with python: Enabling language-aware data products with machine learning. ” O’Reilly Media, Inc.”, 2018.

5. Ronan Collobert, Jason Weston, Léon Bottou, Michael Karlen, Koray Kavukcuoglu, and Pavel Kuksa, “Natural language processing (almost) from scratch,” Journal of machine learning research 12, no. ARTICLE (2011): 2493-2537.

6. Yoav Goldberg, “Neural network methods for natural language processing,” Synthesis lectures on human language technologies 10, no. 1 (2017): 1-309.

7. Yoav Goldberg, “A primer on neural network models for natural language processing,” Journal of Artificial Intelligence Research 57 (2016): 345-420.