Abstract | ||
---|---|---|
Word alignment is a key task in statistical machine translation (SMT). This paper presents a novel model for this task. In this model, word alignment is considered as a multiobjective optimization problem and solved based on the non-dominated sorting genetic algorithm II (NSGA-II), which is one of the best multiobjective evolutionary algorithms (MOEA). There are two advantages of the proposed model based on NSGA-II. First, it could be easily extended through incorporating new objective functions. Secondly, it does not need any hand-aligned word-level alignment data to determine the weight of each objective function. Experiments were carried out and the results show that the proposed model outperforms the IBM translation models significantly. |
Year | DOI | Venue |
---|---|---|
2009 | 10.1016/j.camwa.2008.10.018 | Computers & Mathematics with Applications |
Keywords | Field | DocType |
ibm translation model,word alignment,hand-aligned word-level alignment data,multiobjective evolutionary algorithms (moea),key task,objective function,multiobjective optimization,statistical machine translation (smt),multiobjective evolutionary algorithm,new objective function,novel model,multiobjective optimization problem,word alignment model | Mathematical optimization,IBM,Evolutionary algorithm,Computer science,Machine translation,Multi-objective optimization,Sorting,Artificial intelligence,Multiobjective optimization problem,Genetic algorithm | Journal |
Volume | Issue | ISSN |
57 | 11-12 | Computers and Mathematics with Applications |
Citations | PageRank | References |
1 | 0.35 | 15 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
CHEN Yi-dong | 1 | 106 | 27.34 |
SHI Xiao-dong | 2 | 169 | 21.97 |
Changle Zhou | 3 | 233 | 50.24 |
Q. Y. Hong | 4 | 50 | 15.79 |