Dive into a comprehensive tutorial on Natural Language Processing (NLP) using Python, covering fundamental concepts to advanced techniques. Explore bag-of-words, word vectors, stemming, lemmatization, and spell correction. Learn about transformer architecture and state-of-the-art models like OpenAI GPT and BERT. Gain hands-on experience with popular libraries such as sklearn, spaCy, NLTK, and TextBlob. Build text classification models, implement regex pattern matching, and fine-tune transformer models. Culminate your learning by developing a high-performance model to classify Amazon review categories, suitable for learners of all skill levels.
Overview
Syllabus
- Announcements!
- Video overview & timeline
- Bag of words BOW overview
- Bag of words example code! sklearn | CountVectorizer, fit_transform
- Building a text classification model using bag-of-words SVM
- Predicting new utterances classes using our model transform
- Unigram, bigram, ngrams using consecutive words in your model
- Word vectors overview
- Word vectors example code! Using spaCy library
- Building a text classification model using word vectors
- Predicting new utterances using our model
- Regexes pattern matching in Python.
- Stemming/Lemmatization in Python text normalization w/ NLTK library
- Stopwords Removal removing most common words from sentences
- Various other techniques spell correction, sentiment analysis, part-of-speech tagging.
- Recurrent Neural Networks RNNs for text classification
- Transformer architectures attention is all you need
- Writing Python code to leverage transformers BERT | spacy-transformers
- Writing a classification model using transformers/BERT
- Fine-tuning transformer models
- Bring it all together and build a high performance model to classify the categories of Amazon reviews!
Taught by
Keith Galli
