Sciweavers

763 search results - page 101 / 153
» Stream-based Translation Models for Statistical Machine Tran...
Sort
View
ACL
2006
13 years 9 months ago
Minimum Risk Annealing for Training Log-Linear Models
When training the parameters for a natural language system, one would prefer to minimize 1-best loss (error) on an evaluation set. Since the error surface for many natural languag...
David A. Smith, Jason Eisner
ACL
2006
13 years 9 months ago
Factoring Synchronous Grammars by Sorting
Synchronous Context-Free Grammars (SCFGs) have been successfully exploited as translation models in machine translation applications. When parsing with an SCFG, computational comp...
Daniel Gildea, Giorgio Satta, Hao Zhang
CIKM
2007
Springer
14 years 2 months ago
Combining resources with confidence measures for cross language information retrieval
Query translation in Cross Language Information Retrieval (CLIR) can be performed using multiple resources. Previous attempts to combine different translation resources use simple...
Youssef Kadri, Jian-Yun Nie
CIKM
2005
Springer
14 years 1 months ago
A hybrid approach to NER by MEMM and manual rules
This paper describes a framework for defining domain specific Feature Functions in a user friendly form to be used in a Maximum Entropy Markov Model (MEMM) for the Named Entity Re...
Moshe Fresko, Binyamin Rosenfeld, Ronen Feldman
NIPS
2007
13 years 9 months ago
Expectation Maximization and Posterior Constraints
The expectation maximization (EM) algorithm is a widely used maximum likelihood estimation procedure for statistical models when the values of some of the variables in the model a...
João Graça, Kuzman Ganchev, Ben Task...