440 Huntington Avenue
314 West Village H
Boston, MA 02115
ATTN: Nada Naji, 202 WVH
360 Huntington Avenue
Boston, MA 02115
- Digital Humanities
- Digital Libraries
- PhD in Computer Science in Information Retrieval, University of Neuchatel, Switzerland
- MSc in Computer Information Systems, The Arab Academy for Banking and Financial Sciences, Jordan
- BSc Engr. in Information Technology and Software Engineering, University of Technology in Baghdad
Professor Nada Naji received her PhD in Computer Science in information retrieval from the School of Computer Science (IIUN) at the University of Neuchatel, Switzerland in 2013. Prior to joining Northeastern University, she was a postdoctoral research fellow at the Center for Intelligent Information Retrieval (CIIR) at the University of Massachusetts Amherst since April 2014. Since 2009, her research has been focused on the representation and retrieval of noisy text (e.g. digitized text/OCR, social media textual content) and under-resourced languages (e.g. old languages, modern dialectal/informal variations). She is an awardee of the Swiss National Science Foundation (SNSF) Early Postdoc.Mobility Grant.
Field of research/teaching
What is your educational background?
I received my undergraduate degree from the University of Technology in Baghdad, my masters from the Arab Academy for Banking and Financial Sciences, Jordan, and my doctorate of computer science in Information Retrieval from the University of Neuchatel, Switzerland.
What is your research focus?
Since 2009, my research has focused on the representation and retrieval of texts. I designed and built text analysis tools, low-cost representations, and search engines for datasets of scanned documents and historical manuscripts wherein spelling variations and non-standardized grammar constitute difficult challenges. In addition to multi-lingual information retrieval, I have been working on a new concept that I refer to as “Cross-script information retrieval” which aims to enable the retrieval of textual content in languages that are alternatively and informally written (transliterated) in Roman script as opposed to their official/native writing systems. Such a representation is very widely used in social media such as Twitter, Facebook, blogs, and text messaging (SMS, IM) in certain languages. The main challenges faced here are the lack of transliteration rules, intuitive spelling and non-standardized abbreviations, dialectal and regional variations of the language, and the sparsity of resources such as thesauri and datasets.
What courses/subjects do you teach?
- Information Retrieval
- Fundamentals of Computer Science II
- Discrete Structures