Sciweavers

3716 search results - page 76 / 744
» On the monotonization of the training set
Sort
View
EMNLP
2009
15 years 4 months ago
Feasibility of Human-in-the-loop Minimum Error Rate Training
Minimum error rate training (MERT) involves choosing parameter values for a machine translation (MT) system that maximize performance on a tuning set as measured by an automatic e...
Omar Zaidan, Chris Callison-Burch
ICDE
2008
IEEE
203views Database» more  ICDE 2008»
16 years 7 months ago
Training Linear Discriminant Analysis in Linear Time
Linear Discriminant Analysis (LDA) has been a popular method for extracting features which preserve class separability. It has been widely used in many fields of information proces...
Deng Cai, Xiaofei He, Jiawei Han
EMNLP
2009
15 years 4 months ago
Consensus Training for Consensus Decoding in Machine Translation
We propose a novel objective function for discriminatively tuning log-linear machine translation models. Our objective explicitly optimizes the BLEU score of expected n-gram count...
Adam Pauls, John DeNero, Dan Klein
UM
2010
Springer
15 years 10 months ago
Ranking Feature Sets for Emotion Models Used in Classroom Based Intelligent Tutoring Systems
Abstract. Recent progress has been made by using sensors with Intelligent Tutoring Systems in classrooms in order to predict the affective state of students users. If tutors are a...
David G. Cooper, Kasia Muldner, Ivon Arroyo, Bever...
IWEC
2008
15 years 7 months ago
Experiences Employing Novice Wizard Operators in a Gallery Setting
During a 11-week installation of an immersive augmented reality (AR) experience at an art and technology gallery, we faced the practical challenges of preparing for live public aud...
Steven Dow, Blair MacIntyre