Publications Data Analytics & CS

Arabic e-book reader - an application that supports right-to-left script and other requirements for the Arabic language

NADEEF (which means ''clean'' in Arabic) is an extensible and generalized data cleaning system.  Released as open source, NADEEF allows users to implement their own data repairing algorithms to replace default NADEEF data repair implementation.  

• Research paper (SIGMOD)
• Dashboard (via Github)

The World Bank's Auto Geotagger is a prototype which automatically identifies locations in documents from the World Bank Projects Data API using the Stanford Name Entity Recognizer (NER) and Alchemy, geocodes them with the Google Geocoder, Yahoo! Placefinder , and Geonames and visualizes them on a map.

Humanitarian UAV Network (UAViators). In collaboration with multiple partners. UAViators promotes Big Data solutions for aerial imagery analysis and facilitates the safe & responsible use of UAVs in a wide range of humanitarian settings. UAViators was recently endorsed by the United Nations.

QATS:  QCRI Advanced Transcription System, a state-of-the-art speech recognition system for Modern Standard Arabic, is now live on Aljazeera.net!  Select daily or archived videos and turn on the closed caption feature.
 

A Semi-Automatic and Low Cost Approach to Build Scalable Lemma-based Lexical Resources for Arabic Verbs. International Journal of Information Technology and Computer Science(IJITCS). Vol. 8, No. 2, February 2016. 

IEEE Transactions on Parallel and Distributed Systems, Vol. 24, 2013, pp. 2015-2024.

” MIT CSAIL Technical Report, Report No. MIT-CSAIL-TR-2015-007, March 3, 2015, pp. 1-62. Available online: http://hdl.handle.net/1721.1/95774.

Fine-Grained Sentiment Analysis for Movie Reviews in Bulgarian. In Proceedings of the Conference on Recent Advances in Natural Language Processing (RANLP'2015), Hissar, Bulgaria, September 2015.