Event Details

Cyber Center Distinguished Lecture

April 19 @ 12:00 PM - 1:30 PM - Lawson 3102

Ophir Frieder

Professor and Chair of the Department of Computer Science at Georgetown University


  'Searching in the "Real World"'

For many, "searching" is considered a mostly solved problem.  In fact, for text processing, this belief is factually based.  The problem is that most "real world" search applications involve "complex documents", and such applications are far from solved.  Complex documents, or less formally, "real world documents", comprise of a mixture of images, text, signatures, tables, etc, and are often available only in scanned hardcopy formats.  Search systems for such document collections are currently unavailable.  We describe our efforts at building a complex document information processing prototype.  This prototype integrates "point solution" (mature) echnologies, such as OCR capability, signature matching and handwritten word spotting techniques, search and mining approaches, among others, to yield a system capable of searching "real world documents".  The described prototype demonstrates the adage that "the whole is greater than the sum of its parts".  Our complex document benchmark development efforts are likewise presented.


Having described the global approach, we describe some potential future point solutions which we have developed over the years.  These include an Arabic stemmer and a natural language source integration fabric called the Intranet Mediator.  In terms of stemming, we developed and commercially licensed an Arabic stemmer and search system.  Our approach was evaluated using the benchmark Arabic collections and favorably compared against the state of the art.


We also focused on source integration and ease of user interaction. By integrating structured and unstructured sources, we developed and commercially licensed our mediator technology that provides a single, natural language interface to querying distributed sources.  Rather than providing a set of links as possible answers, the described approach actually answers the posed question.  Both the Arabic stemmer and the mediator efforts are likewise discussed.



Purdue University, West Lafayette, IN 47907 (765) 494-4600

© 2016 Purdue University | An equal access/equal opportunity university | Copyright Complaints | Maintained by the Office of the Executive Vice President for Research and Partnerships

If you have trouble accessing this page because of a disability, please contact the Office of the Executive Vice President for Research and Partnerships at evprp@purdue.edu.