Pivot Lightly-Supervised Training for Statistical Machine Translation

In this paper, we investigate large-scale lightly-supervised training with a pivot language: We augment a baseline statistical machine translation (SMT) system that has been trained on human-generated parallel training corpora with large amounts of additional unsupervised parallel data; but instead of creating this synthetic data from monolingual source language data with the baseline system itself, or from target language data with a reverse system, we employ a parallel corpus of target language data and data in a pivot language. The pivot language data is automatically translated into the source language, resulting in a trilingual corpus with unsupervised source language side. We augment our baseline system with the unsupervised sourcetarget parallel data. Experiments are conducted for the GermanFrench language pair using the standard WMT newstest sets for development and testing. We obtain the unsupervised data by translating the English side of the English-French 10 corpus to German. With careful system design, we are able to achieve improvements of up to +0.4 points BLEU / -0.7 points TER over the baseline.