English

An Investigation of the Sampling-Based Alignment Method and Its Contributions

Computation and Language 2013-08-22 v1

Abstract

By investigating the distribution of phrase pairs in phrase translation tables, the work in this paper describes an approach to increase the number of n-gram alignments in phrase translation tables output by a sampling-based alignment method. This approach consists in enforcing the alignment of n-grams in distinct translation subtables so as to increase the number of n-grams. Standard normal distribution is used to allot alignment time among translation subtables, which results in adjustment of the distribution of n- grams. This leads to better evaluation results on statistical machine translation tasks than the original sampling-based alignment approach. Furthermore, the translation quality obtained by merging phrase translation tables computed from the sampling-based alignment method and from MGIZA++ is examined.

Keywords

Cite

@article{arxiv.1308.4479,
  title  = {An Investigation of the Sampling-Based Alignment Method and Its Contributions},
  author = {Juan Luo and Yves Lepage},
  journal= {arXiv preprint arXiv:1308.4479},
  year   = {2013}
}

Comments

11 pages

R2 v1 2026-06-22T01:12:31.300Z