Farsi eOrthography: an example of eOrthography Concept

1
Farsi e-Orthography an example of e-Orthography
Concept

• Behrang Qasemizadeh

2
What is e-Orthography and Why Do We Need That?

• e-Orthography tells us
• How the orthography of a language can be followed
  in an encoding system
• What character codes should be used
• How they attach to each other to form a word
• Which tokenization policy must be taken in
  document processing
• Interaction between the policy of text encoding,
  tokenization, orthography, and text processing
  e.g. Corpus tagging
• E-Orthography is an implied assumption in any
  text analysis application

3
e-Orthography is a Must for Some Languages

• Farsi, an Indo-European language, is written with
  Arabic transcription! (a Semitic Language,
  cursive transcription)
• Words can represent with different forms
  (different codes, different keys)
• Available standards do not tell us how they
  should represent in digital environment or at
  least what are the equal keys
• Solution e-Orthography