In this paper, we present a novel extension of a forest-to-string machine translation system with a reordering model. We predict reordering probabilities for every pair of source words with a model using features observed from the input parse forest. Our approach naturally deals with the ambiguity present in the input parse forest, but, at the same time, takes into account only the parts of the input forest used by the current translation hypothesis. The method provides improvement from 0.6 up to 1.0 point measured by (Ter − Bleu)/2 metric.
Paper
Full text
Reordering Model for Forest-to-String Machine Translation
Semantic Scholar · Computer Science · 2014
Abstract
In this paper, we present a novel extension of a forest-to-string machine translation system with a reordering model. We predict reordering probabilities for every pair of source words with a model using features observed from the input parse forest. Our approach naturally deals with the ambiguity present in the input parse forest, but, at the same time, takes into account only the parts of the input forest used by the current translation hypothesis. The method provides improvement from 0.6 up to 1.0 point measured by (Ter − Bleu)/2 metric.