Edinburgh Neural Machine Translation Systems for WMT 16
Rico Sennrich, Barry Haddow, Alexandra Birch
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/rsennrich/wmt16-scriptsOfficialIn papernone★ 0
Abstract
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.
Tasks
Benchmark Results
| Dataset | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| WMT2016 Czech-English | Attentional encoder-decoder + BPE | BLEU score | 31.4 | — | Unverified |
| WMT2016 English-Czech | Attentional encoder-decoder + BPE | BLEU score | 25.8 | — | Unverified |
| WMT2016 English-German | Attentional encoder-decoder + BPE | BLEU score | 34.2 | — | Unverified |
| WMT2016 English-Romanian | BiGRU | BLEU score | 28.1 | — | Unverified |
| WMT2016 English-Russian | Attentional encoder-decoder + BPE | BLEU score | 26 | — | Unverified |
| WMT2016 German-English | Attentional encoder-decoder + BPE | BLEU score | 38.6 | — | Unverified |
| WMT2016 Romanian-English | Attentional encoder-decoder + BPE | BLEU score | 33.3 | — | Unverified |
| WMT2016 Russian-English | Attentional encoder-decoder + BPE | BLEU score | 28 | — | Unverified |