Orthographic Word Segmentation Task

An Orthographic Word Segmentation Task is a text tokenization task that requires the Detection of Orthographic Words in a Written Expression.

• AKA: OWST, Written Word Segmentation Task.
• Context:
  • Input: a Written Linguistic Expression, typically from a Segmented Written Language.
  • output: a Word Sequence.
  • It can be solved by an Orthographic Word Segmentation System.
• Example(s):
  • OWST("I'm coming home") ⇒ ([I'm] [coming] [home]).
  • OWST("I bought a real time operating system") ⇒ ([I] [bought] [a] [real] [time] [operating] [system]).
  • ...
• Counter-Example(s):
  • PWST(I'mcominghome) ⇒ ([I'm] [coming] [home]).
  • TTT("I'm coming home") ⇒ ([I] ['m] [coming] [home]).
  • VWST("I bought a real time operating system") ⇒ ([I] [bought] [a] [real time] [operating system]).
  • VWST("日文章魚怎麼說") ⇒ ([日文] [章魚] [怎麼] [說]) (i.e. ~[Japanese] [octopus] [how] [say]).
• See: Grapheme Segmentation Task, Phonological Word Segmentation Task, Spoken Word Segmentation Task.

References

• Concept