ITAI 2373 Natural Language Processing

Fundamental concepts in Natural Language Processing (NLP) and text processing. Focus on knowledge and skills necessary to create a language recognition application.

Credits

3

Offered

Spring

Outcomes

1. Describe common techniques in Natural Language Processing and associated applications.
2. Describe data acquisition process in NLP and how it contrasts depending on datasets being used. Appreciate various storage methods used for NLP datasets.
3. Explore common NLP focused libraries such as NLTK, TextBlob, spaCY, Gensim and data visualization techniques.
4. Apply data preprocessing techniques (like document similarity, Word Vectors, Cosine similarity etc.) and describe ML Models (like Naive Bayes Classifier, Decision Tree Classifier, Random Forest Classifier etc.).
5. Compare and describe different Neural Language Models.
6. Implement Language Detection, Transliteration, Translation, Sentiment Analysis for different language scenarios.
7. Develop Python-based use cases & AI Projects incorporating above learnings and techniques.
8. Apply different tools like Chatteron and deploy them using Heroku to create chatbots.
9. Discuss & describe advanced models in NLP.