Nadir Durrani

Nadir Durrani


University of Stuttgart, School of Computer Science, Electrical Engineering and Information Technology, Institute for Natural Language Processing (IMS), Azenbergstr. 12, D-70174, Stuttgart, Germany. Cel: 0049 176-64698489

Email: last name @ Domain:







NEW: I have moved to the University of Edinburgh, see my new home page here


I was a doctoral student at the Institute of Natural Language Processing (IfNLP), University of Stuttgart, starting in April 2008. I was advised by Alex Fraser and Helmut Schmid. Before going to Stuttgart I was at the Center for Research in Urdu Language Processing where I worked with Prof. Sarmad Hussain.


My research interests include:


Natural Language Processing: statistical machine translation and transliteration, word segmentation, studying different writing scripts and their complexities in terms of font development, normalization, language collation.


Localization: localization of open source operating systems (desktop environment KDE/GNOME), word processing applications (Open Office), chatting tools (Psi), web browsers (Sea Monkey, Mozilla) and web development tools (NVU), localization of domain names


Last winter, I was a research intern at IBM T.J Watson Center. I worked on the front-end processing of the Egyptian blog data with Yaser Al-Onaizan, Abraham Ittycheriah, Rong Zhang and Salim Roukos.  The overall goal was to improve Egyptian-to-English Machine Translation system by mapping Egyptian words into MSA words.


My PhD thesis is an extension of N-gram based SMT. However, we are using sequence of operations rather than sequence of tuples (bilingual translation units). An operation can be to translate a set of words or to perform reordering. The translation and reordering operations are coupled in a single generative story such that the reordering decisions may depend on preceding translation decisions and translation decisions may depend on preceding reordering decisions. This provides a natural reordering mechanism which is able to deal with local and long-distance reorderings in a consistent way.


Last year, I presented my thesis work at the StatNLP doctoral seminar. You can see my slides here.


Previously, I worked on a Hindi-to-Urdu Machine Translation System. Hindi and Urdu are closely related language pairs with a very large vocabulary overlap, but they are written in different scripts. We tried to make use of this by integrating a transliteration model inside the translation system. It worked!!!


I’ll be defending my thesis later this year and am looking for a job/post-doctoral position now.  Please contact me if you think I will be a good fit in your group.


Here’s a periodically updated CV and a list of my publications.


If you play Chess, catch me online here.  Can you imagine applying the principles of Chess in Tai Chi (martial arts) and vice versa? Get this book !!!