Command Palette
Search for a command to run...
Rico Sennrich; Barry Haddow; Alexandra Birch
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.
Code Repositories
Benchmarks
| Benchmark | Methodology | Metrics |
|---|---|---|
| machine-translation-on-wmt2016-czech-english | Attentional encoder-decoder + BPE | BLEU score: 31.4 |
| machine-translation-on-wmt2016-english | Attentional encoder-decoder + BPE | BLEU score: 26.0 |
| machine-translation-on-wmt2016-english-1 | BiGRU | BLEU score: 28.1 |
| machine-translation-on-wmt2016-english-czech | Attentional encoder-decoder + BPE | BLEU score: 25.8 |
| machine-translation-on-wmt2016-english-german | Attentional encoder-decoder + BPE | BLEU score: 34.2 |
| machine-translation-on-wmt2016-german-english | Attentional encoder-decoder + BPE | BLEU score: 38.6 |
| machine-translation-on-wmt2016-romanian | Attentional encoder-decoder + BPE | BLEU score: 33.3 |
| machine-translation-on-wmt2016-russian | Attentional encoder-decoder + BPE | BLEU score: 28.0 |
Build AI with AI
From idea to launch — accelerate your AI development with free AI co-coding, out-of-the-box environment and best price of GPUs.