Sciweavers

2980 search results - page 156 / 596
» Learning better together
Sort
View
NAACL
2007
15 years 7 months ago
Source-Language Features and Maximum Correlation Training for Machine Translation Evaluation
We propose three new features for MT evaluation: source-sentence constrained n-gram precision, source-sentence reordering metrics, and discriminative unigram precision, as well as...
Ding Liu, Daniel Gildea
NAACL
2004
15 years 7 months ago
Exponential Priors for Maximum Entropy Models
Maximum entropy models are a common modeling technique, but prone to overfitting. We show that using an exponential distribution as a prior leads to bounded absolute discounting b...
Joshua Goodman
IMCSIT
2010
15 years 4 months ago
TREF - TRanslation Enhancement Framework for Japanese-English
Abstract--We present a method for improving existing statistical machine translation methods using an knowledge-base compiled from a bilingual corpus as well as sequence alignment ...
Bartholomäus Wloka, Werner Winiwarter
KDD
2006
ACM
155views Data Mining» more  KDD 2006»
16 years 6 months ago
Single-pass online learning: performance, voting schemes and online feature selection
To learn concepts over massive data streams, it is essential to design inference and learning methods that operate in real time with limited memory. Online learning methods such a...
Vitor R. Carvalho, William W. Cohen
AH
2008
Springer
16 years 23 days ago
A Validation Framework for Formal Models in Adaptive Work-Integrated Learning
The focus of my thesis is on the development of a multi-method framework for the validation of formal models (domain model, user model, and teaching model) for adaptive work-integr...
Barbara Kump