ABSTRACT:
This presentation will outline two algorithms to understand phonetically
written text. Given a new word, the objective of these algorithms is to
determine its pronunciation. The first algorithm does this by training a
probabilistic model, and the second uses a set of decision rules. Two
applications are presented, namely microtext normalization, where we match
new words written online to similar-sounding English words, and
alliteration analysis of medieval literature.
Bio: Richard Khoury received his Bachelor's Degree and his Master's Degree in
Electrical and Computer Engineering from Laval University in 2002 and 2004
respectively, and his Doctorate in Electrical and Computer Engineering
from the University of Waterloo in 2007. Since August 2008, he is a
faculty member in the Department of Software Engineering at Lakehead
University. Dr. Khoury's primary area of research is natural language
processing, but his research interests also include data mining, knowledge
management, machine learning, and artificial intelligence. He was the
guest editor for a special issue of the Journal of Emerging Technologies
in Web Intelligence dedicated to the growing field of Web Data Mining. He
has over 30 peer-reviewed publications and $400,000 in research funding,
and has won a Contribution to Teaching Award at Lakehead University. He is
an adjunct professor in the Department of Software Engineering at Laval
University, where he is currently doing his sabbatical year. Off-campus,
he has served as president of the Rotary Club of Thunder Bay (Fort
William) in 2013-2014, and is a founding member of "Ohm Base", Thunder
Bay's first hackerspace, a public community technology lab that
contributes to the spreading of technology awareness in the community and
to the fostering of local talent.
|