Final Exam: Natural Language Processing Fundamentals

WHAT YOU WILL LEARN

• 

  Provide an overview of natural language processing and how it can be supported by the natural language toolkit (nltk) and spacy
  

  list the preprocessing steps for natural language processing
  

  perform tokenization with nltk
  

  perform tokenization with spacy
  

  remove stopwords using spacy
  

  perform stemming with nltk
  

  perform lemmatization with nltk
  

  provide an overview of sentiment analysis
  

  perform sentiment analysis with vader
  

  train models on tf-idf encodings
  

  train classification models on n-grams
  

  explore bag-of-words and bag-of-ngrams encoding
  

  encode text as count vectors
  

  use the countvectorizer object for one-hot encoding
  

  encode data using term frequency–inverse document frequency (tf-idf) scores
  

  train a classification model on text embeddings
  

  work with pre-trained glove embeddings
  

  train a gaussian naive bayes model on glove embeddings
• 

  describe deep learning with tensorflow
  

  train a dnn model
  

  view the tensorboard callback output
  

  generate term frequency-inverse document frequency (tf-idf) encodings for text
  

  train a dnn on word embeddings
  

  train a cnn for sentiment analysis
  

  train a simple rnn memory cell
  

  train rnns with long short-term memory (lstm) and bidirectional lstm
  

  use pre-trained embeddings from the tensorflow hub
  

  perform subword tokenization with wordpiece
  

  train the fnet model for sentiment analysis
  

  compute text similarity with the use
  

  preprocess data for language translation
  

  calculate the loss and accuracy for a translation model
  

  train and generate predictions using an encoder-decoder model
  

  calculate query, key, and value for transformer models
  

  set up the encoder and decoder