Paper Info
Title
EDA: AN EVOLUTIONARY DECODING ALGORITHM FOR STATISTICAL MACHINE TRANSLATION
Abstract
In a statistical machine translation system (SMTS), decoding is the process of finding the most likely translation based on a statistical model, according to previously learned parameters. The success of an SMTS is strongly dependent on the quality of its decoder. Most of the SMTS's published in current literature use approaches based on traditional optimization methods and heuristics. On the other hand, over the last few years there has been a rapid increase in the use of metaheuristics. These kinds of techniques have shown to be able to solve difficult search problems in an efficient way for a wide number of applications. This paper proposes a new approach based on evolutionary hybrid algorithms to translate sentences in a specific technical context. The algorithm has been enhanced by adaptive parameter control. The tests are carried out in the context of Spanish and then translated to English. The experimental results validate the superior performance of our method in contrast to a statistical greedy decoder. We also compare our new approach to the existing public domain general translators.
Year
DOI
Venue
2007
10.1080/08839510701492546
Applied Artificial Intelligence
Keywords
Field
DocType
statistical machine translation,evolutionary decoding algorithm,specific technical context,difficult search problem,statistical machine translation system,likely translation,evolutionary hybrid algorithm,statistical model,adaptive parameter control,statistical greedy decoder,new approach,current literature use,hybrid algorithm,public domain
Public domain,Computer science,Machine translation system,Machine translation,Algorithm,Heuristics,Artificial intelligence,Statistical model,Decoding methods,Parameter control,Machine learning,Metaheuristic
Journal
Volume
Issue
ISSN
21
7
0883-9514
Citations 
PageRank 
References 
2
0.43
17
Authors
2
Name
Order
Citations
PageRank
Eridan Otto151.19
María Cristina Riff220023.91