1. Intro NLP
2. Strings in Python. Pandas. Jupyter Notebook
3. Preprocessing. Regular expression
4. Scikit-learn. Bag-of-word. Byte-pair-encoding. TFIDF. LDA, LSA
5. Scikit-learn. Logistic Regression. Clustering
6. Minimum edit distance. TextDistance library
7. NLTK. Preprocessing
8. NLTK. Classification. Clustering
9. N-gram Language Model
10. Part of Speech Tagging. Markov Chains
11. Abstract Meaning Representation
12. FastAPI. Pydantic
- Word Embedding. PCA
- Word2Vec. Preprocessing
- Word2Vec. Euclidian distance. Cosine distance
- Word2Vec. Models
- K-nearest neighbors. Hash tables and hash functions. Locality sensitive hashing. Multiple Planes. Approximate nearest neighbors. Searching documents
- Spacy. Preprocessing
- Spacy. Models. Training models
- Spacy. NER. Sentencizer. TextCategorizer
- Spacy. Pipelines. Trasformers
- FastText
13. Scraping. Parsing. Beautiful Soup
- Neural networks intro. Keras
- CNN for text classification
- RNN. Char RNN. Word RNN
- Named Entity Recognition system using an LSTM
- Siamese networks
- Seq-to-Sec models
- Neural Machine Translation model with Attention
- HuggingFace. Transformers
- HuggingFace. Text Summarization. Question Answering
В кінці курсу виконується дипломний проєкт.