[SSC] Behrang Mohit: Localization of Difficult-to-Translate Phrases

[Mohsen Taghaddosi]

A Seminar by *Behrang Mohit*, PHD Student in Intelligent Systems
Program,University of Pittsburgh


Title:Localization of Difficult-to-Translate Phrases

Time and Place: Tuesday, April 14th, 2008, 12:20-1:20pm at Khawrazmi Hall,
CE Department, Sharif University of Technology

Abstract:
    Over the past decade, Statistical Machine Translation (SMT) has been the
dominant paradigm
among the Machine Translation researchers.  I present an overview of the SMT
framework
with a focus on the phrase-based SMT.  Moreover, I present our recent work
on the "translation difficulty".
 We formulate the notion of difficulty as a measurable quantity; we show
that a classifier can be trained to
predict whether a phrase might be difficult to translate; and we develop a
framework that makes use of
the classifier and external resources (such as human translators) to improve
the overall translation quality.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://lists.ce.sharif.edu/pipermail/ssc/attachments/20080413/fa9ee1c7/attachment.htm