Natural Language Processing – Basics

Natural Language Processing

• Making computers understand and deal with natural (human) languages like English, Tamil, Spanish, etc.
• Exploiting human cleverness, and not computer cleverness

Natural Language Processing is a field of Computer Science and Linguistics concerned with the interactions between computers and natural (human) languages.

Categories

Phonology

• Modeling the pronunciation of a word as a string of symbols – PHONES
• Involves study of syllables, how they sound and how they group together to produce the word sound.
• Notice the difference in sound of “C” in the following words:
  • Coach
  • Chair
  • Can

Morphology

• Identification, analysis and description of the structure of words.
• Study of structural variations of words
• INFLECTIONS in a word are structural changes, usually through affixes, to express Number, Tense, Case, Gender, Person, etc.
  • dog – dogs
  • goose – geese
  • hunt – hunted
  • his – hers
• WORD FORMATIONS includes a group of words that have a specific meaning when they appear together.
  • mother in law
  • hot dog

Syntax

• Study of grammars
• Syntactic correctness in sentence formation
• Part of Speech tagging
  • Noun
  • Verb
  • Adjective, etc
• I can write : Is “can” AUX VERB or VERB or NOUN?

Semantics

• Understanding and representing the meaning

 



A simple semantic network

• Predicate Calculus can be used to represent semantics: Has(Ram, book)

Browse through the below presentation for more information on

• NLP
• Ambiguity resolution
• Perceptions
• Applications of NLP
• Machine Learning