Abstract
This paper presents the NICT's participation to the WMT18 shared news translation task. We participated in the eight translation directions of four language pairs: Estonian-English, Finnish-English, Turkish-English and Chinese-English. For each translation direction, we prepared state-of-the-art statistical (SMT) and neural (NMT) machine translation systems. Our NMT systems were trained with the transformer architecture using the provided parallel data enlarged with a large quantity of back-translated monolingual data that we generated with a new incremental training framework. Our primary submissions to the task are the result of a simple combination of our SMT and NMT systems. Our systems are ranked first for the Estonian-English and Finnish-English language pairs (constraint) according to BLEU-cased.
Abstract (translated)
本文介绍了NICT参与WMT18共享新闻翻译任务的情况。我们参加了四种语言对的八个翻译方向:爱沙尼亚语 - 英语,芬兰语 - 英语,土耳其语 - 英语和中英文。对于每个翻译方向,我们准备了最先进的统计(SMT)和神经(NMT)机器翻译系统。我们的NMT系统使用变换器架构进行了培训,使用提供的并行数据,并使用新的增量培训框架生成大量的反向翻译单语数据。我们对该任务的主要提交是我们的SMT和NMT系统的简单组合的结果。根据BLEU的说法,我们的系统在爱沙尼亚语 - 英语和芬兰 - 英语语言对(约束)中排名第一。
URL
https://arxiv.org/abs/1809.07037