Generalized Character-Level Spelling Error Correction
Noura Farra, Nadi Tomeh, Alla Rozovskaya, Nizar Y. Habash · 2014
We present a generalized discriminative model for spelling error correction which targets character-level transformations.While operating at the character level, the model makes use of wordlevel and contextual information.In contrast to previous work, the proposed approach learns to correct a variety of error types without guidance of manuallyselected constraints or language-specific features.We apply the model to correct errors in Egyptian Arabic dialect text, achieving 65% reduction in word error rate over the input baseline, and improving over the earlier state-of-the-art system.Action % Errors Example Error ⇒ Reference Substitute 80.9 E Alif A forms ( / / / AÂ/ Ǎ/ Ā) 33.3 AHdhm ⇒ ÂHdhm ⇒ E Ya / forms ( y/ý) 26.7 ςly ⇒ ςlý ⇒