ARWI: Arabic Write and Improve

2025-04-16

AI Summary

A severe scarcity of Arabic writing assistance tools impedes the development of academic writing proficiency among Modern Standard Arabic (MSA) learners. Method: We propose the first open-source writing support system tailored for MSA learners, integrating a multi-level prompt library, a Transformer-based grammatical error correction (GEC) model, CEFR-aligned multidimensional automated scoring, a lightweight text editor, and a dynamic prompt engineering framework. The system introduces the first publicly available, hierarchically structured writing prompt database and supports self-expanding corpus annotation to facilitate contrastive error pattern analysis between native speakers and L2 learners. Contribution/Results: Preliminary user studies demonstrate significant improvements in learners’ grammatical error detection accuracy and self-revision efficiency. Concurrently, we initiate the construction of a high-quality, expert-annotated Arabic GEC and automated scoring benchmark dataset.

Technology Category

• Natural Language Processing: Sentiment Analysis, Stylistic Analysis, and Argument Mining
• Machine Learning: Large Multimodal Models (LMMs)
• Cognitive Modeling & Cognitive Systems: Computational Creativity

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Systems and Infrastructure for Web, Mobile and WoT: Web performance, measurement, and characterization
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data

Abstract

Although Arabic is spoken by over 400 million people, advanced Arabic writing assistance tools remain limited. To address this gap, we present ARWI, a new writing assistant that helps learners improve essay writing in Modern Standard Arabic. ARWI is the first publicly available Arabic writing assistant to include a prompt database for different proficiency levels, an Arabic text editor, state-of-the-art grammatical error detection and correction, and automated essay scoring aligned with the Common European Framework of Reference standards for language attainment. Moreover, ARWI can be used to gather a growing auto-annotated corpus, facilitating further research on Arabic grammar correction and essay scoring, as well as profiling patterns of errors made by native speakers and non-native learners. A preliminary user study shows that ARWI provides actionable feedback, helping learners identify grammatical gaps, assess language proficiency, and guide improvement.

Problem

• Lack of advanced Arabic writing assistance tools
• Need for Arabic grammatical error detection and correction
• Absence of automated Arabic essay scoring standards

Innovation

• First Arabic writing assistant with multi-level prompts
• State-of-the-art Arabic grammar error correction
• Auto-annotated corpus for Arabic learning research