NYU Abu Dhabi and MBZUAI researchers have developed ARWI, a free web application to help Arabic language learners improve their writing skills in Modern Standard Arabic. ARWI provides essay prompts aligned with CEFR skill levels, features an Arabic text editor, and gives personalized feedback. The tool won the Diversity Award at the Workshop on Intelligent and Interactive Writing Assistants (In2Writing). Why it matters: This tool can help preserve the quality and personal voice of Arabic writing amid the rise of LLMs.
This article discusses retrieval augmentation in text generation, where information retrieved from an external source is used to condition predictions. It references recent work on retrieval-augmented image captioning, showing that model size can be greatly reduced when training data is available through retrieval. The author intends to continue this work focusing on the intersection of retrieval augmentation and in-context learning, and controllable image captioning for language learning materials. Why it matters: This research direction has the potential to improve transfer learning in vision-language models, which could be especially relevant for downstream applications in Arabic NLP and multimodal tasks.
Ted Briscoe from the University of Cambridge discussed using machine learning and NLP to develop learning-oriented assessment (LOA) for non-native writers. The technology is used in Cambridge English courseware like Empower and Linguaskill, as well as Write and Improve. Briscoe is also the co-founder and CEO of iLexIR Ltd. Why it matters: Improving automated language assessment could significantly enhance online language learning platforms in the Arab world and beyond.