Scribd
Upload
29 views2 pages

NLP Syllabus

The CAP370 Natural Language Processing course covers key concepts, applications, and challenges of NLP, along with practical techniques such as text preprocessing and deep learning model fine-tuning. Students will engage in hands-on experiments using Python libraries like NLTK, TensorFlow, and spaCy to implement various NLP tasks, including sentiment analysis and text classification. The course also explores advanced topics like prompt engineering and machine learning methods in NLP.

Uploaded by

muskandeepk803
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
29 views2 pages

NLP Syllabus

The CAP370 Natural Language Processing course covers key concepts, applications, and challenges of NLP, along with practical techniques such as text preprocessing and deep learning model fine-tuning. Students will engage in hands-on experiments using Python libraries like NLTK, TensorFlow, and spaCy to implement various NLP tasks, including sentiment analysis and text classification. The course also explores advanced topics like prompt engineering and machine learning methods in NLP.

Uploaded by

muskandeepk803
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

CAP370:NATURAL LANGUAGE PROCESSING

L:2 T:0 P:2 Credits:3

Course Outcomes: Through this course students should be able to

CO1 :: describe the key concepts, applications, and challenges of Natural Language Processing
(NLP).

CO2 :: practice various text preprocessing techniques such as tokenization, stemming,


lemmatization, and stop-word removal using NLTK, TextBlob, and Pandas.

CO3 :: experiment and fine-tune deep learning models (RNN, LSTM, BERT, GPT) using
TensorFlow/Keras to perform tasks like sentiment analysis, text classification, and text
generation.
CO4 :: analyze different word representation methods and parsing techniques to analyze
sentence structures and semantic meaning.

CO5 :: demonstrate end-to-end NLP pipelines incorporating text preprocessing, feature


extraction, and machine learning models, optimizing them for tasks like chatbots, information
retrieval, and document classification.
CO6 :: compare the effectiveness of supervised, unsupervised, and deep learning-based NLP
models using performance metrics such as accuracy, precision, recall, and F1-score, and suggest
improvements.

Unit I
Introduction to Natural Language Processing : Definition, applications and use cases of NLP,
Steps in NLP, Finding structure of Words, sentences, syntax, and semantics, Phonetics, morphology,
pragmatics, phonology, Natural Language processing with NLTK
Unit II
Language Models and Text Processing : Text Preprocessing with Python: Reading & Writing files,
string manipulation, Regular Expression, Text Cleaning, Tokenization using NLTK, Text Analysis
Libraries of Text Processing, Native Python, Textblob, Pandas, Stop-word removal, stemming, and
lemmatization., Word Representations: Bag of Words (BoW), TF-IDF using sklearn
Unit III
Syntax and Parsing Techniques : Grammar Formalisms: Context-Free Grammar (CFG), Chomsky
Normal Form, Parsing Techniques: Implementing parsers in Python using libraries like nltk,
Applications of Parsing: Sentence structure analysis, Semantic role labeling
Unit IV
Semantic Analysis : Lexical Semantics in Python, Discourse Semantics in Python, Semantic
Similarity: Ontology and Knowledge Representation, Semantic Web libraries in Python (e.g., RDFLib),
Implementing sentiment analysis using Python libraries (TextBlob, VADER)
Unit V
Advanced NLP Techniques : Machine Learning in NLP: Supervised and unsupervised methods using
sklearn, Deep Learning in NLP: Recurrent Neural Networks (RNNs), Long Short-Term Memory (LSTM)
using TensorFlow/Keras, Transformers and Transformers library, Pre-trained Models: Fine-tuning
BERT, GPT System Overview, Text Generation: Basics of Natural Language Generation (NLG) with
Python
Unit VI
Prompt Engineering : Core Principles, Types of prompts, Comman Challenges & Solutions, Advance
Techniques: Zero-Shot Learning, Few-Shot Learning, COT (Change of Thought), Reinforcement
through iteration

List of Practicals / Experiments:

Practical Applications of NLP


• Write a Python script to demonstrate basic NLP operations using NLTK, including tokenization, POS
tagging, and chunking.
• . Implement a script to identify phonetic representations and morphological structures of words using
NLTK or related libraries.
• Create a script to perform the following tasks on a dataset:Read and write text files. Clean text
(remove special characters, numbers, etc.).Tokenize sentences and words.

Session 2024-25 Page:1/2


• Use Python's re module to perform pattern matching on text, such as extracting email addresses,
phone numbers, and hashtags.
• Compare text preprocessing using NLTK, TextBlob, and Pandas. Perform stop-word removal,
stemming, and lemmatization on a given dataset.
• Implement Bag of Words (BoW) and TF-IDF vectorization using sklearn. Use the vectors to compute
cosine similarity between sentences.
• . Define a Context-Free Grammar (CFG) for a small subset of English and use NLTK to parse
sentences according to the grammar.
• Write a Python script to perform constituency and dependency parsing on sentences using spaCy

• Develop a Python script to analyze stock prices.

• Create GUI for weather forecast

• Perform sentiment analysis on a dataset (e.g., movie reviews) using TextBlob and VADER. Compare
the results of both libraries.
• Use Python's rdflib library to create and query a simple ontology. Demonstrate basic RDF and
SPARQL operations.
• Implement a Recurrent Neural Network (RNN) or LSTM to classify text sequences (e.g., classify
movie reviews as positive or negative) using TensorFlow/Keras.
• Use Transformers to fine-tune a BERT or GPT model for a text classification task (e.g., spam email
detection).

Text Books:
1. UNDERSTANDING NATURAL LANGUAGE PROCESSING by T V GEETHA, PEARSON

References:
1. MACHINE LEARNING by TOM M. MITCHELL, Mc Graw Hill Education

Session 2024-25 Page:2/2

You might also like