School of Computing and Information Sciences
Deya Banisakher is a PhD candidate working on Natural Language Processing (NLP) in the Cognac Laboratory (Cognition, Narrative, and Culture) under the supervision of Dr. Mark Finlayson and Dr. Naphtali Rishe. His research interests lie within semantic extraction, document understanding, and discourse analysis. Deya received his B.S. in Computer Engineering and Computer Science from Bethune-Cookman University and M.S. in Computer Science from FIU.
Modeling natural human behavior in understanding written language is crucial for developing true artificial intelligence. For people, words convey certain semantic concepts. While documents represent an abstract concept—they are collections of text organized in some logical structure, that is, sentences, paragraphs, sections, and so on. Like words, these document structures, are used to convey a logical flow of semantic concepts. Machines, however, only view words as spans of characters and documents as mere collections of free-text, missing any underlying meanings behind words and the logical structure of those documents.
Automatic semantic concept detection is the process by which the underlying meanings of words are identified and retrieved. My thesis aims at bridging the semantic gap between automatic concept detection and logical document structure understanding. In my dissertation, I demonstrate an analysis and development of a framework for using logical document structure knowledge (that is, section structure) in detecting semantic concepts within documents in various domains. In that, I developed my research around six different document classes from four domains: medical, legal, scientific, and news reporting. The document classes are as follows: psychiatric report evaluations, hospital discharge summaries, and radiology reports in the medical domain; Patent documents in the legal domain; environmental journal articles in the scientific domain; Finally, business and politics news articles.