NICT's Neural and Statistical Machine Translation Systems for the WMT18 News Translation Task
This work addresses translation quality improvements for news translation tasks, but it is incremental as it builds on existing methods.
The paper tackled machine translation for eight language directions by developing state-of-the-art statistical and neural systems, achieving first-place rankings in BLEU-cased scores for Estonian-English and Finnish-English pairs.
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.