The RWTH Aachen University Supervised Machine Translation Systems for WMT 2018
The RWTH Aachen University Supervised Machine Translation Systems for WMT 2018
复制标题
亚琛工业大学监督机器翻译系统参加 WMT 2018
DOI：
10.18653/v1/w18-6426
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
H. Ney
中科院分区：
文献类型：
--
作者：
Julian Schamper;Jan Rosendahl;Parnia Bahar;Yunsu Kim;Arne F. Nix;H. Ney
本文介绍了亚琛工业大学为EMNLP 2018第三届机器翻译会议（WMT 2018）的德语→英语、英语→土耳其语和汉语→英语翻译任务开发的统计机器翻译系统。我们使用基于Transformer架构的神经机器翻译系统。我们的主要重点是德语→英语的任务，我们所有的自动得分首先与尊重指标提供的组织者。我们确定数据选择，微调，批量大小和模型维度作为重要的超参数。总的来说，我们比去年提交的BLEU提高了6.8%，比2017年德语→英语任务的获胜系统提高了4.8%。在英语→土耳其语的任务中，我们显示BLEU比去年的获胜系统提高了3.6%。我们进一步报告了中文→英文任务的结果，我们比基线系统平均提高了2.2%的BLEU，但仍落后于2018年的获奖系统。
This paper describes the statistical machine translation systems developed at RWTH Aachen University for the German→English, English→Turkish and Chinese→English translation tasks of the EMNLP 2018 Third Conference on Machine Translation (WMT 2018). We use ensembles of neural machine translation systems based on the Transformer architecture. Our main focus is on the German→English task where we to all automatic scored first with respect metrics provided by the organizers. We identify data selection, fine-tuning, batch size and model dimension as important hyperparameters. In total we improve by 6.8% BLEU over our last year’s submission and by 4.8% BLEU over the winning system of the 2017 German→English task. In English→Turkish task, we show 3.6% BLEU improvement over the last year’s winning system. We further report results on the Chinese→English task where we improve 2.2% BLEU on average over our baseline systems but stay behind the 2018 winning systems.