Advancements in Arabic Grammatical Error Detection and Correction: An Empirical Investigation

TL;DR

This paper introduces new Transformer-based models for Arabic grammatical error detection and correction, demonstrating improved performance and establishing benchmarks in a morphologically complex language.

Contribution

It presents the first multi-class Arabic GED task, integrates GED info into GEC models, and explores morphological preprocessing, advancing Arabic GEC research.

Findings

Models achieve state-of-the-art results on Arabic GEC datasets.

GED information improves GEC performance.

Morphological preprocessing aids error correction.

Abstract

Grammatical error correction (GEC) is a well-explored problem in English with many existing models and datasets. However, research on GEC in morphologically rich languages has been limited due to challenges such as data scarcity and language complexity. In this paper, we present the first results on Arabic GEC using two newly developed Transformer-based pretrained sequence-to-sequence models. We also define the task of multi-class Arabic grammatical error detection (GED) and present the first results on multi-class Arabic GED. We show that using GED information as an auxiliary input in GEC models improves GEC performance across three datasets spanning different genres. Moreover, we also investigate the use of contextual morphological preprocessing in aiding GEC systems. Our models achieve SOTA results on two Arabic GEC shared task datasets and establish a strong benchmark on a recently created dataset. We make our code, data, and pretrained models publicly available.