Sciweavers

120 search results - page 2 / 24
» How Much Can We Gain from Supervised Word Alignment
Sort
View
ACL
2006
13 years 11 months ago
Discriminative Word Alignment with Conditional Random Fields
In this paper we present a novel approach for inducing word alignments from sentence aligned data. We use a Conditional Random Field (CRF), a discriminative model, which is estima...
Phil Blunsom, Trevor Cohn
WSC
2008
14 years 20 days ago
How much is a health insurer willing to pay for Colorectal Cancer screening tests?
Colorectal Cancer (CRC) screening tests have proven to be cost-effective in preventing cancer incidence. Yet, as recent studies have shown, CRC screening tests are noticeably unde...
Reza Yaesoubi, Stephen D. Roberts
ACL
2008
13 years 11 months ago
Better Alignments = Better Translations?
Automatic word alignment is a key step in training statistical machine translation systems. Despite much recent work on word alignment methods, alignment accuracy increases often ...
Kuzman Ganchev, João Graça, Ben Task...
JSYML
2010
114views more  JSYML 2010»
13 years 8 months ago
The Ackermann functions are not optimal, but by how much?
By taking a closer look at the construction of an Ackermann function we see that between any primitive recursive degree and its Ackermann modification there is a dense chain of p...
Harold Simmons
ACL
2011
13 years 2 months ago
Rare Word Translation Extraction from Aligned Comparable Documents
We present a first known result of high precision rare word bilingual extraction from comparable corpora, using aligned comparable documents and supervised classification. We in...
Emmanuel Prochasson, Pascale Fung