Natural Language Processing
Informacje ogólne
Kod przedmiotu: | 4010-NLP |
Kod Erasmus / ISCED: |
(brak danych)
/
(0619) Komputeryzacja (inne)
|
Nazwa przedmiotu: | Natural Language Processing |
Jednostka: | Interdyscyplinarne Centrum Modelowania Matematycznego i Komputerowego |
Grupy: | |
Punkty ECTS i inne: |
6.00
|
Język prowadzenia: | (brak danych) |
Skrócony opis: |
This course provides an overview of natural language processing (NLP) on modern Intel® architecture. Topics include: 1. How to manipulate text for language models 2. Text generation and topic modeling 3. The basics of machine learning through more advanced concepts |
Pełny opis: |
1. History of NLP. Topics include: a. The history of natural language processes and how it is used in the industry today b. How to parse strings using powerful regular expression tools in Pytho 2. NLP toolkits and preprocessing techniques. Topics include: a. Explore techniques such as tokenization, stop-word removal, and punctuation manipulation b. Implement such techniques using Python libraries such as NLTK, TextBlob, spaCy, and Gensim 3. Similarity between words. Learn more about: a. Levenshtein distance, which is used to compare the similarity of two words b. How computers encode pieces of text into a document-term matrix and what the bag of words assumption is 4. Basic text classification. Topics include: a. The basics of machine learning and a refresher on the terminology b. A typical machine learning workflow for two different machine learning approaches to classify emails as either spam or not spam 5. Algorithm for natural language understanding and topic modeling. Learn more about: a. How to use the latent Dirichlet allocation algorithm to extract topics from the document-term matrices 6. How to model and extract topics in text. Learn more about: a. Alternative algorithms for discovering the topics embedded in texts 7. Machine learning algorithms for NLP. a. How to use a neural network to transform words into vectors b. Potential applications of these vectors (such as text classification and information retrieval) 8. Applying neural networks. Topics include: a.Text generation using Markov chains and recurrent neural networks b. Advanced topics in NLP, such as seq2seq |
Literatura: |
Intel Academy: https://www.intel.com/content/www/us/en/developer/learn/course-natural-language-processing.html |
Efekty uczenia się: |
By the end of this course, students will have practical knowledge of: 1. Application of string preprocessing techniques 2. How to apply machine learning algorithms for text classification and other language tasks |
Metody i kryteria oceniania: |
Zaliczenie na podstawie samodzielnie opracowanego raportu na zadany temat (analiza przykladowych danych). |
Zajęcia w cyklu "Semestr zimowy 2022/23" (zakończony)
Okres: | 2022-10-01 - 2023-01-29 |
![]() |
Typ zajęć: |
Laboratorium, 30 godzin
Wykład, 30 godzin
|
|
Koordynatorzy: | Łukasz Górski | |
Prowadzący grup: | (brak danych) | |
Lista studentów: | (nie masz dostępu) | |
Zaliczenie: | Egzamin |
Zajęcia w cyklu "Semestr letni 2022/23" (w trakcie)
Okres: | 2023-02-20 - 2023-06-18 |
![]() |
Typ zajęć: |
Laboratorium, 30 godzin
Wykład, 30 godzin
|
|
Koordynatorzy: | Łukasz Górski | |
Prowadzący grup: | (brak danych) | |
Lista studentów: | (nie masz dostępu) | |
Zaliczenie: | Egzamin |
Właścicielem praw autorskich jest Uniwersytet Warszawski, Wydział Nauk Ekonomicznych.