Abdullah Khered is a PhD candidate in the Department of Computer Science at The University of Manchester, where he also completed his MSc degree with a focus on natural language processing. His doctoral research centres on the normalisation of Arabic text from social media, aiming to convert informal and dialectal Arabic into a standard form suitable for downstream language tasks. In particular, his work addresses the challenges of translating multiple Dialectal Arabic (DA) varieties into Modern Standard Arabic (MSA) by leveraging advanced neural methods and publicly available dialectal corpora. 

Abdullah’s recent research includes the development of neural machine translation systems using pretrained Arabic models for dialect-to-MSA normalisation, integrating these with dialect identification in a multi-task setting, as well as the creation of new parallel resources from social media. He has also conducted evaluations of these models on manually verified datasets of multiple dialects.