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.
@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}
}