log in  |  register  |  feedback?  |  help  |  web accessibility
Efficiency Enhancement Tools for Arabic Text Search and Processing
Wednesday, December 11, 2013, 11:00 am-12:00 pm Calendar
  • You are subscribed to this talk through .
  • You are watching this talk through .
  • You are subscribed to this talk. (unsubscribe, watch)
  • You are watching this talk. (unwatch, subscribe)
  • You are not subscribed to this talk. (watch, subscribe)

In this talk we report on a series of efficiency enhancement tools that were developed an deployed to simplify dealing with Arabic text retrieval and processing. The tools mainly use a statistical approach and are based on a corpus of Modern Standard Arabic (MSA) texts. The tools include Query preprocessing (expansion, suggestion, correction), Wikipedia Based Text Categorization and Categorized Spell-Checking and Arabic Persons' Names processing tools. Time permitting we may mention explorations into legacy Arabic texts and Dialects processing.


Adnan Yahya is a Professor at the Department of Computer Systems Engineering, Birzeit University, Palestine. He received his PhD degree from Northwestern University in 1984. He had several visiting appointments at universities and research centers in the US and Europe including longer term stays at UMD/UMIACS, Duke University, The University of Munich and Koblenz University.

Areas of interest include Automated/Nonmonotoinc Reasoning, Arabic NLP and Information Retrieval. Adnan Yahya is a member of the ACM, IEEE and IEEE-Computer Society.

The research reported in this talk was supported in part by a Google Research Award (2009).

This talk is organized by Jimmy Lin