Sciweavers

119 search results - page 11 / 24
» Better Evaluation Metrics Lead to Better Machine Translation
Sort
View
EMNLP
2008
14 years 11 months 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
15 years 3 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
15 years 10 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
14 years 7 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»
15 years 1 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