NATURAL LANGUAGE PROCESSING (2/2 Credits)

Learning Outcomes:

On successful completion of this course, student will be able to: LO1 – describe what is Natural Language Processing and its components; LO2 – explain Explain fundamental concepts of how to work with Natural Language Processing; LO3 – apply Natural Language Processing concepts in certain real-world applications; LO4 – construct Natural Language Processing applications.

Topics:

1. Language and Computation;
2. N-Grams and Part-of-Speech;
3. Corpus; Naïve Bayes & Sentiment Classification;
4. Classification & Logistic Regression;
5. Vector Semantics & Embeddings;
6. Progress Project Presentation;
7. Neural Networks & Neural Language Models;
8. Constituency Grammars & Parsing;
9. Dependency Parsing;
10. Semantic Role Labeling;
11. Chatbots;
12. Final Project Presentation;
13. Intro to Natural Language Toolkit (Tokenization, Stop Words);
14. Stemming, Lemmatization;
15. POS Tagging;
16. TF-IDF and Cosine Similarity;
17. Sentiment Classification with Naïve Bayes;
18. Quiz;
19. Language Model (N-Grams);
20. Word Embedding;
21. Grammar Parsing with NLTK;
22. Dependency Parsing with Spacy;
23. Name Entity Recognition; Final Exam.