Week 1
Introduction to Natural Language Processing (NLP) and Python Basics.
Week 2
Text Preprocessing and Tokenization
Week 3
Week 4
Maximum Likelihood Estimation (MLE)
Week 5
Week 6
Long short-term memory (LSTM) and gated recurrent units (GRU)
Week 7
Word Embeddings in NLP Applications
Week 8
Encoder-Decoder Architecture for Sequence-to-Sequence Tasks
Week 9
Attention in Sequence-to-Sequence Models
Week 10
Supervised Learning for Sentiment Analysis
Week 11
Transfer learning for emotion detection
Week 12
Leveraging Deep Learning Models for Sentiment Analysis
Week 13
Emotion Detection Using Pre-Trained Transformer Models: BERT
Week 14
Using sentiment analysis to generate emotionally appropriate responses
Week 15
Sequence Labeling for Named Entity Recognition Using Conditional Random Fields
Week 16
Dependency Parsing Algorithms and Libraries
Week 17
Text Summarization: Abstractive and Extractive Approaches
Research Stay – Final Project
In natural language processing, accurately detecting and classifying emotions from textual data is a pivotal challenge, with far-reaching applications in sentiment analysis, customer feedback interpretation, and human-computer interaction. This final project is designed to provide students with hands-on experience in this intricate domain of machine learning. The task involves the preparation, analysis, and emotion annotation of a text dataset, employing three distinct computational approaches: rule-based, neural networks, and deep learning.