Learning Outcomes
- Proficiency in various text representation models used in Natural Language Processing (NLP) and Information Retrieval (IR).
- Ability to apply and utilize Bag of Words and tf-idf techniques for text representation and feature extraction.
- Understanding the fundamentals of information retrieval and its various methods.
- Mastery in using vector-space methods for information retrieval tasks.
- Familiarity with evaluation metrics used in assessing the performance of information retrieval systems.
- Understanding different language models used specifically in information retrieval.
- Proficiency in various word representation models used in NLP tasks.
- Ability to work with word embeddings like word2vec for semantic representation of words.
- Understanding and practical knowledge of Transformer-based models such as BERT and GPT for language understanding and generation tasks.
- Ability to apply NLP techniques in various application-specific contexts, such as sentiment analysis, text classification, or named entity recognition.
- Understanding techniques used in content-based retrieval systems for multimedia data.
Course Content
Text representation models
Bag of words, tf-idf
Information retrieval
Vector-space methods for IR
Information retrieval evaluation metrics
IR and language models
Word representation models
RNN-LSTM
Transformers – BERT, GPT
Application-specific NLP
Content-based multimedia retrieval
