The Karlsruhe Institute of Technology Systems for the News Translation Task in WMT 2018

By Thanh-Le Ha, Eunah Cho, Jan Niehues, Mohammed Mediani, Matthias Sperber, Alexander Allauzen, A. Waibel. 2018

10 citations recorded by the source corpus.

We present our experiments in the scope of the news translation task in WMT 2018, in directions: English→German. The core of our systems is the encoder-decoder based neural machine translation models using the transformer architecture. We enhanced the model with a deeper architecture. By using techniques to limit the memory consumption, we were able to train models that are 4 times larger on one GPU and improve the performance by 1.2 BLEU points. Furthermore, we performed sentence selection for the newly available ParaCrawl corpus. Thereby, we could improve the effectiveness of the corpus by 0.5 BLEU points.

Subfields: Machine Translation

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Machine Translation

1. A. Waibel
2. Jan Niehues
3. Thanh-Le Ha

Citations in the corpus

• Findings of the 2018 Conference on Machine Translation (WMT18) (2018, neutral): “2.4.11 KIT (Pham et al., 2018) The KIT submission is the NMT Transformer architecture, enhanced in model depth.”
• Very Deep Self-Attention Networks for End-to-End Speech Recognition (2019, background): “er normalization is the key to enable greater depth configurations to be trainable, which is the main reason for the performance breakthrough in recent works in both MT and natural language processing [8, 14]. 2.4. Stochastic Layers The high density of residual connections is the reason why Transform”
• Pre-Translation for Neural Machine Translation (2016, background): “A detailed description of the systems can be found in (Ha et al., 2016).”