Orthographic Error Correction (OrthEC) Task

An Orthographic Error Correction (OrthEC) Task is a text error correction task that focuses on orthographic/typographic errors.

• AKA: Typographic Mistake Repair.
• Context:
  • It can range from being a Manual Orthographic Error Correction Task to being an Automatic Orthographic Error Correction Task (solved by an orthographic error correction system that implements an orthographic error correction algorithm).
  • It can be supported by a Typographical Error Detection Task.
  • It can (typically) include Misspelling Correction, Miscapitalization Correction, and Mispunctuation Correction.
  • …
• Example(s):
  • OrthEC(“Weres th eeror?”) ⇒ “Where's the error?”.
  • OrthEC(“iliked yester days weaather.”) ⇒ “I liked yesterday's weaather.”.
  • OrthEC(“I visitted Tokyo on Nov 2003.:)”) ⇒ “I visitted Tokyo on Nov 2003.:)”.
  • OrthEC(“Kan yu reed dis massage despiet thehorible sppelingm sitakes?”) ⇒ “Can you read this message despite the horrible sppelling mistakes?”.
  • …
  • Misspelling Corrections, such as ...
  • Miscapitalization Correction, such as: ...
  • Mispunctuation Correction, such as: ...
  • …
• Counter-Example(s):
  • Grammatical Error Correction.
  • Shallow WikiText Error Correction.
• See: Character-Level Text Error Correction.

---

---

References

1991

• (Mays et al., 1991) ⇒ Eric Mays, Fred J.Damerau, Robert L. Mercer. “Context Based Spelling Correction", In: Information Processing & Management 27(5). DOI:10.1016/0306-4573(91)90066-U
  • ABSTRACT: Some mistakes in spelling and typing produce correct words, such as typing “fig” when “fog” was intended. These errors are undetectable by traditional spelling correction techniques. In this paper we present a statistical technique capable of detecting and correcting some of these errors when they occur in sentences. Experimental results show that this technique is capable of detecting 76% of simple spelling errors and correcting 73%.

---