Mohab Elkaref

Hi, I'm Mohab

I'm a PhD research student in the School of Computer Science at the University of Birmingham. I am supervied by Dr. Bernd Bohnet and Prof. John Barnden.

My current focus is on Deep Learning applications for Dependency Parsing. Another aspect of my research is the relation between Syntactic and Semantic dependencies.

Previous work included domain adaptation with self-training and automatically generating frames in the FrameNet format for Arabic.

My general research interests are Deep Learning, Natural Language Processing, Speech Recognition, Artificial Intelligence and Cognitive Science.

2015

  • Juntao Yu, Mohab Elkaref, and Bernd Bohnet. 2015. Domain Adaptation for Dependency Parsing via Self-training. In Proceedings of the 14th International Conference on Parsing Technologies (IWPT), pages 1-10, Bilbao, Spain, July. Association for Computational Linguistics.

2014

  • Viktor Pekar, Juntao Yu, Mohab Elkaref, and Bernd Bohnet. 2014. Exploring Options for Fast Domain Adaptation of Dependency Parsers. In Proceedings of the First Joint Workshop on Statistical Parsing of Morphologically Rich Languages and Syntactic Analysis of Non-Canonical Languages (SPMRL-SANCL), pages 54-65, Dublin, Ireland, August. Dublin City University.

2015, Spring, University of Birmingham

  • Team Project (Teaching Assistant)
  • Natural Language Processing 1 (Teaching Assistant)

2014, Autumn, University of Birmingham

  • Introduction to Databases (Teaching Assistant)

2012, German University in Cairo

  • Software Engineering (Junior Teaching Assistant)

In my spare time I make games and occasionaly take part in Ludum Dare, go hiking or try some calligraphy. And beware, I know very basic kung fu! You have been warned!

My Masters topic focused on using Genetic Programming to generate code for AI. An example application of this was to generate an AI for the Robocode programming game. This AI took part and won Second place in the GECCO '13 competition.

University of Birmingham
School of Computer Science (building Y9)
Birmingham B15 2TT
Office 218

Email: mxe346 [at] cs [dot] bham [dot] ac [dot] uk