Attention-based Encoder-Decoder Networks for Spelling and Grammatical Error Correction

TL;DR

This paper explores neural sequence-to-sequence and attention-based models for automatic spelling and grammatical error correction, demonstrating their effectiveness and adaptability across languages.

Contribution

It introduces neural machine translation models for error correction, showing their success and potential for application to various languages.

Findings

Neural models outperform traditional methods in error correction.

Attention mechanisms improve correction accuracy.

Models trained on Arabic data generalize well to other languages.

Abstract

Automatic spelling and grammatical correction systems are one of the most widely used tools within natural language applications. In this thesis, we assume the task of error correction as a type of monolingual machine translation where the source sentence is potentially erroneous and the target sentence should be the corrected form of the input. Our main focus in this project is building neural network models for the task of error correction. In particular, we investigate sequence-to-sequence and attention-based models which have recently shown a higher performance than the state-of-the-art of many language processing problems. We demonstrate that neural machine translation models can be successfully applied to the task of error correction. While the experiments of this research are performed on an Arabic corpus, our methods in this thesis can be easily applied to any language.