Log In Sign Up

NICT's Neural and Statistical Machine Translation Systems for the WMT18 News Translation Task

by   Benjamin Marie, et al.

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.


page 1

page 2

page 3

page 4


Neural System Combination for Machine Translation

Neural machine translation (NMT) becomes a new approach to machine trans...

The Helsinki Neural Machine Translation System

We introduce the Helsinki Neural Machine Translation system (HNMT) and h...

SJTU-NICT's Supervised and Unsupervised Neural Machine Translation Systems for the WMT20 News Translation Task

In this paper, we introduced our joint team SJTU-NICT 's participation i...

NICT's Corpus Filtering Systems for the WMT18 Parallel Corpus Filtering Task

This paper presents the NICT's participation in the WMT18 shared paralle...

Combining SMT and NMT Back-Translated Data for Efficient NMT

Neural Machine Translation (NMT) models achieve their best performance w...

Simple Fusion: Return of the Language Model

Neural Machine Translation (NMT) typically leverages monolingual data in...