Home

About

Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network
FAQHELPSITE MAPCONTACT US


  Advanced Search  

 
Forest Reranking for Machine Translation with the Perceptron Algorithm Zhifei Li and Sanjeev Khudanpur
 

Summary: Forest Reranking for Machine Translation with the Perceptron Algorithm
Zhifei Li and Sanjeev Khudanpur
Center for Language and Speech Processing and Department of Computer Science
Johns Hopkins University, Baltimore, MD 21218, USA
zhifei.work@gmail.com and khudanpur@jhu.edu
Abstract
We present a scalable discriminative training
framework for parsing-based statistical ma-
chine translation. Our framework exploits hy-
pergraphs (or packed forests) to compactly
encode exponentially many competing trans-
lations, and uses the perceptron algorithm to
learn to discriminatively prefer the oracle-best
tree in the hypergraph. To facilitate training,
we present: (i) an oracle extraction algorithm
to efficiently extract the oracle trees from a hy-
pergraph that best match the reference transla-
tions; (ii) a hypergraph pruning algorithm that
substantially reduces the disk space required
for storing the hypergraphs without degrading

  

Source: Amir, Yair - Department of Computer Science, Johns Hopkins University

 

Collections: Computer Technologies and Information Sciences