Majdi Sawalha

The fact that the Natural Language Processing group is a pioneer in procesing Arabic text and that the University of one of top 100 universities in the world meant that Leeds was the perfect choice for me.

My research is "Part-of-Speech Tagging for Arabic Text";. The main aim of doing this research is to widen the scope of part-of-speech taggers and morphological analyzers to process text of different domains, formats and genres, of both vowelized and non-vowelized text. This research involves a study of existing morphological analyzers and stemmers of Arabic Text, using gold standard for evaluation. Then, we developing a morphological analyzer for Arabic text that mainly depends on linguistic information extracted from traditional Arabic grammar books. 

The purpose of the research is to develop a domain and genre independent fine-grain part-of-speech tagger and morphological analyzer. These applications will be used to annotate Arabic corpora with fine-grain morphological tags that encode all of the morphological features of the words in the corpus. 

How does your research apply to real world applications?

My research will help to Annotate corpora with annotate Arabic corpora with fine-grain morphological tags. It Can be used to build language teaching applications for researchers and Arabic language learners and it is used in developing language resources, such as; dictionaries, lexicons, thesauruses, WordNets, machine translators and learning materials that help native speakers, learners and researchers. Arabic is also a key technology that is required in terrorism detection applications. Part-of-speech tagging and morphological analysers of Arabic have to be an essential technology for developing anomalous detection systems.

What facilities and special equipment do you use to carry out your research? 

I use Computer facilities in the school as well as the fantastic Language resources, traditional Arabic grammar books from the Universities huge library, Lexicons and WordNets, Corpora – Corpus of contemporary Arabic, Penn Arabic Treebank, and the Qur’an.

What do you enjoy about your research? 

I really enjoy working with the Natural Language Processing research group who are a great team!

University life and studying and living in the UK has also been really easy to get settled into. I enjoy working hard and being productive by publishing research papers in international conferences. I also participate in prestigious international conferences by presenting my work there and discussing and sharing ideas with scholars from all over the world.

Why did you choose to undertake a PhD at the University of Leeds?

I chose Leeds because the NLP group at the University is a pioneer in processing Arabic text. Leeds University is also one of the top 100 universities in the world and the School of Computingis one of the top 10 in the UK for research.

What are your ambitions for the future?

After graduating I plan to transfer my knowledge to my home country, to establish a research group, NLP group for processing Arabic and also establish my own business.