Sciweavers

283 search results - page 17 / 57
» Improving Statistical Word Alignment with Ensemble Methods
Sort
View
ACL
2009
13 years 5 months ago
Data Cleaning for Word Alignment
Parallel corpora are made by human beings. However, as an MT system is an aggregation of state-of-the-art NLP technologies without any intervention of human beings, it is unavoida...
Tsuyoshi Okita
LREC
2010
188views Education» more  LREC 2010»
13 years 9 months ago
How Large a Corpus Do We Need: Statistical Method Versus Rule-based Method
We investigate the impact of input data scale in corpus-based learning using a study style of Zipf's law. In our research, Chinese word segmentation is chosen as the study ca...
Hai Zhao, Yan Song, Chunyu Kit
BMCBI
2008
113views more  BMCBI 2008»
13 years 7 months ago
Investigating selection on viruses: a statistical alignment approach
Background: Two problems complicate the study of selection in viral genomes: Firstly, the presence of genes in overlapping reading frames implies that selection in one reading fra...
Saskia de Groot, Thomas Mailund, Gerton Lunter, Jo...
CICLING
2010
Springer
13 years 2 months ago
A Chunk-Driven Bootstrapping Approach to Extracting Translation Patterns
Abstract. We present a linguistically-motivated sub-sentential alignment system that extends the intersected IBM Model 4 word alignments. The alignment system is chunk-driven and r...
Lieve Macken, Walter Daelemans
PR
2010
158views more  PR 2010»
13 years 5 months ago
Out-of-bag estimation of the optimal sample size in bagging
The performance of m-out-of-n bagging with and without replacement in terms of the sampling ratio (m/n) is analyzed. Standard bagging uses resampling with replacement to generate ...
Gonzalo Martínez-Muñoz, Alberto Su&a...