7 papers
Learning Source Phrase Representations for Neural Machine Translation
Hongfei Xu, Josef van Genabith, Deyi Xiong +2
The Transformer translation model (Vaswani et al., 2017) based on a multi-head attention mechanism can be computed effectively in parallel and has significantly pushed forward the…
Dynamically Adjusting Transformer Batch Size by Monitoring Gradient Direction Change
Hongfei Xu, Josef van Genabith, Deyi Xiong +1
The choice of hyper-parameters affects the performance of neural models. While much previous research (Sutskever et al., 2013; Duchi et al., 2011; Kingma and Ba, 2015) focuses on a…
Probing Word Translations in the Transformer and Trading Decoder for Encoder Layers
Hongfei Xu, Josef van Genabith, Qiuhui Liu +1
Due to its effectiveness and performance, the Transformer translation model has attracted wide attention, most recently in terms of probing-based approaches. Previous work focuses…
Lipschitz Constrained Parameter Initialization for Deep Transformers
Hongfei Xu, Qiuhui Liu, Josef van Genabith +2
The Transformer translation model employs residual connection and layer normalization to ease the optimization difficulties caused by its multi-layer encoder/decoder structure. Pre…
The Transference Architecture for Automatic Post-Editing
Santanu Pal, Hongfei Xu, Nico Herbig +3
In automatic post-editing (APE) it makes sense to condition post-editing (pe) decisions on both the source (src) and the machine translated text (mt) as input. This has led to mult…
UdS Submission for the WMT 19 Automatic Post-Editing Task
Hongfei Xu, Qiuhui Liu, Josef van Genabith
In this paper, we describe our submission to the English-German APE shared task at WMT 2019. We utilize and adapt an NMT architecture originally developed for exploiting context in…