Sciweavers

577 search results - page 27 / 116
» Improved Text Generation Using N-gram Statistics
Sort
View
ICONIP
2008
14 years 11 months ago
Local Feature Selection in Text Clustering
Abstract. Feature selection has improved the performance of text clustering. Global feature selection tries to identify a single subset of features which are relevant to all cluste...
Marcelo N. Ribeiro, Manoel J. R. Neto, Ricardo Bas...
ACL
2008
14 years 11 months ago
Combining Multiple Resources to Improve SMT-based Paraphrasing Model
This paper proposes a novel method that exploits multiple resources to improve statistical machine translation (SMT) based paraphrasing. In detail, a phrasal paraphrase table and ...
Shiqi Zhao, Cheng Niu, Ming Zhou, Ting Liu, Sheng ...
BMCBI
2005
125views more  BMCBI 2005»
14 years 9 months ago
A simple approach for protein name identification: prospects and limits
Background: Significant parts of biological knowledge are available only as unstructured text in articles of biomedical journals. By automatically identifying gene and gene produc...
Katrin Fundel, Daniel Güttler, Ralf Zimmer, J...
AAI
1999
91views more  AAI 1999»
14 years 9 months ago
Multilingual Natural Language Generation for Multilingual Software: A Functional Linguistic Approach
In this paper we present an implemented account of multilingual linguistic resources for multilingual text generation that improves significantly on the degree of re-use of resour...
John A. Bateman, Christian Matthiessen, Licheng Ze...
PAMI
2008
190views more  PAMI 2008»
14 years 9 months ago
Scene Classification Using a Hybrid Generative/Discriminative Approach
We investigate whether dimensionality reduction using a latent generative model is beneficial for the task of weakly supervised scene classification. In detail we are given a set ...
Anna Bosch, Andrew Zisserman, Xavier Muñoz