AraSpell: A Deep Learning Approach for Arabic Spelling Correction

TL;DR

AraSpell is a deep learning framework for Arabic spelling correction that employs seq2seq models like RNN and Transformer, trained on extensive artificial data, demonstrating significant improvements over baseline error rates.

Contribution

Introduces AraSpell, a novel Arabic spelling correction system using seq2seq models and artificial data generation, with extensive empirical validation.

Findings

Achieved 4.8% WER and 1.11% CER on test data

Significant reduction in error rates compared to baseline

Validated effectiveness on a large dataset of 100K sentences

Abstract

Spelling correction is the task of identifying spelling mistakes, typos, and grammatical mistakes in a given text and correcting them according to their context and grammatical structure. This work introduces "AraSpell," a framework for Arabic spelling correction using different seq2seq model architectures such as Recurrent Neural Network (RNN) and Transformer with artificial data generation for error injection, trained on more than 6.9 Million Arabic sentences. Thorough experimental studies provide empirical evidence of the effectiveness of the proposed approach, which achieved 4.8% and 1.11% word error rate (WER) and character error rate (CER), respectively, in comparison with labeled data of 29.72% WER and 5.03% CER. Our approach achieved 2.9% CER and 10.65% WER in comparison with labeled data of 10.02% CER and 50.94% WER. Both of these results are obtained on a test set of 100K sentences.