NLP in general

Interdisciplinary field that concerns interactions between computers and technology.

Natural languages are Italian, Chinese… all the languages people speak.

It is split between computer science and linguistics:

• phonetics
  • sounds
• phonology
  • sound systems
• morphology
  • formation and internal structs of the words
• syntax
  • formation and internal structs of sentences
• semantics
  • meaning of the sentences
• pragmatics
  • sentences with semantic meanings are used for communication goals

Some Applications

Siri, Cortana, Autocomplete, spell checking, machine translations

Milestones

NLP Milestones are split into:

• Rule-based
• Statistical and Classical ML Models
• Deep Learning Models

See NLP Milestones for more.

Text normalization

• Before doing any operation we must normalize the text

1. Tokenizing words (see Word Segmentation)
2. Normalizing word formats
3. Segmenting sentences