Natural Language Processing

Natural Language Processing (NLP)

Foundation of Natural Language Processing

  • Overview computational linguistic.
  • History of NLP
  • Why NLP
  • Use of NLP
  • Language modelling with N-gram
  • Spelling correction
  • Neural networks and neural language models
  • Parts-of-Speech tagging
  • Syntactic parsing
  • Language semantics
  • Computational semantics

Text Analytics, Processing, and Predictive Modelling

  • Introduction to text analytics (text encoding, regular expressions*, word frequencies & stop words, tokenization, bag-of-words representation, stemming & lemmatization, TF-IDF)
  • The Naive Bayes algorithm (Bayes’ theorem and its building blocks, Naive Bayes for text classification)

Text Processing Importing text.

  • Web scrapping.
  • Text processing
  • Understanding regex.
  • Text normalization
  • Word count.
  • Frequency distribution.
  • Text annotation.
  • Use of annotator.
  • String tokenization
  • Annotator creation.
  • Sentence processing.
  • Lemmatization in text processing
  • POS.
  • Named entity recognition
  • Dependency parsing in text.
  • Sentimental analysis

Word embedding

  • Word embedding
  • Co-occurrence vectors
  • Word2vec
  • Doc2vec

RNN for NLP

  • Recurrent neural networks.
  • Long short term memory (LSTM)
  • Bi LSTM.
  • Stacked LSTM
  • GRU implementation.
  • Building a story writer using character level RNN.

Attention based model

  • Seq2Seq.
  • Encoders and decoders.
  • Attention mechanism.
  • Attention neural networks
  • Self-attention

Transfer learning in NLP

  • Introduction to transformers.
  • Bert model.
  • Elmo model.
  • GPT2 model
  • GPT3 model.
  • Albert model.
  • Distilbert model

Transformers for NLP

  • GPT3
  • BERT

NLP Libraries

Spacy

  • Spacy overview
  • Spacy function
  • Spacy function implementation in text processing.
  • Pos tagging, challenges and accuracy.
  • Entities and named entry recognition
  • Interpolation, language models
  • NLTK
  • Text blob
  • Stanford NLP