Natural Language Processing (labs), summer 2017/2018
Labs, Poznan University of Technology, Poland, Faculty of Computing, 2018
A 30 hours long practical course on natural language processing
Topics covered:
- Regular expressions
- Text classification with bag of words and TF-IDF
- Word Embeddings
- Natural language generation with Markov Chains
- Recurrent and convolutional neural networks for text classification
- Conditional Random Fields for the problem of Named Entity Recognition
- Topic detection with Latent Dirichlet Allocation
- Text summarization with key-sentence selection
- Textual resources collecting by crawling and HTML parsing
Technologies used: Python, Google Colaboratory, NumPy, SKLearn, Gensim, Keras, NLTK, SpaCy