Edinburgh Neural Machine Translation Systems for WMT 16

by   Rico Sennrich, et al.

We participated in the WMT 2016 shared news translation task by building neural translation systems for four language pairs, each trained in both directions: English<->Czech, English<->German, English<->Romanian and English<->Russian. Our systems are based on an attentional encoder-decoder, using BPE subword segmentation for open-vocabulary translation with a fixed vocabulary. We experimented with using automatic back-translations of the monolingual News corpus as additional training data, pervasive dropout, and target-bidirectional models. All reported methods give substantial improvements, and we see improvements of 4.3--11.2 BLEU over our baseline systems. In the human evaluation, our systems were the (tied) best constrained system for 7 out of 8 translation directions in which we participated.


page 1

page 2

page 3

page 4


LIUM Machine Translation Systems for WMT17 News Translation Task

This paper describes LIUM submissions to WMT17 News Translation Task for...

Improving Neural Machine Translation Models with Monolingual Data

Neural Machine Translation (NMT) has obtained state-of-the art performan...

The University of Edinburgh's Neural MT Systems for WMT17

This paper describes the University of Edinburgh's submissions to the WM...

Graph-based Filtering of Out-of-Vocabulary Words for Encoder-Decoder Models

Encoder-decoder models typically only employ words that are frequently u...

Confidence through Attention

Attention distributions of the generated translations are a useful bi-pr...

Facebook FAIR's WMT19 News Translation Task Submission

This paper describes Facebook FAIR's submission to the WMT19 shared news...

CUNI Systems for the Unsupervised News Translation Task in WMT 2019

In this paper we describe the CUNI translation system used for the unsup...

Code Repositories



view repo

Please sign up or login with your details

Forgot password? Click here to reset