Sciweavers

119 search results - page 11 / 24
» Better Evaluation Metrics Lead to Better Machine Translation
Sort
View
EMNLP
2008
14 years 9 days ago
Phrase Translation Probabilities with ITG Priors and Smoothing as Learning Objective
The conditional phrase translation probabilities constitute the principal components of phrase-based machine translation systems. These probabilities are estimated using a heurist...
Markos Mylonakis, Khalil Sima'an
ISSRE
2005
IEEE
14 years 4 months ago
A Novel Method for Early Software Quality Prediction Based on Support Vector Machine
The software development process imposes major impacts on the quality of software at every development stage; therefore, a common goal of each software development phase concerns ...
Fei Xing, Ping Guo, Michael R. Lyu
ICML
2001
IEEE
14 years 11 months ago
Learning to Select Good Title Words: An New Approach based on Reverse Information Retrieval
In this paper, we show how we can learn to select good words for a document title. We view the problem of selecting good title words for a document as a variant of an Information ...
Rong Jin, Alexander G. Hauptmann
ACL
2009
13 years 8 months ago
Transliteration Alignment
This paper studies transliteration alignment, its evaluation metrics and applications. We propose a new evaluation metric, alignment entropy, grounded on the information theory, t...
Vladimir Pervouchine, Haizhou Li, Bo Lin
ERCIMDL
1999
Springer
138views Education» more  ERCIMDL 1999»
14 years 3 months ago
Disambiguation Strategies for Cross-Language Information Retrieval
Abstract. This paper gives an overview of tools and methods for CrossLanguage Information Retrieval (CLIR) that are developed within the Twenty-One project. The tools and methods a...
Djoerd Hiemstra, Franciska de Jong