Machine Translation
Machine translation is the task of translating a sentence in a source language to a different target language.
Approaches for machine translation can range from rule-based to statistical to neural-based. More recently, encoder-decoder attention-based architectures like BERT have attained major improvements in machine translation.
One of the most popular datasets used to benchmark machine translation systems is the WMT family of datasets. Some of the most commonly used evaluation metrics for machine translation systems include BLEU, METEOR, NIST, and others.
( Image credit: Google seq2seq )
Papers
Showing 2001–2025 of 10752 papers
All datasetsWMT2014 English-GermanWMT2014 English-FrenchIWSLT2014 German-EnglishACESWMT2016 English-RomanianWMT2016 Romanian-EnglishWMT2014 German-EnglishIWSLT2015 German-EnglishWMT2016 English-GermanIWSLT2015 English-VietnameseIWSLT2015 English-GermanWMT2016 German-English
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | Transformer Cycle (Rev) | BLEU score | 35.14 | — | Unverified |
| 2 | Noisy back-translation | BLEU score | 35 | — | Unverified |
| 3 | Transformer+Rep(Uni) | BLEU score | 33.89 | — | Unverified |
| 4 | T5-11B | BLEU score | 32.1 | — | Unverified |
| 5 | BiBERT | BLEU score | 31.26 | — | Unverified |
| 6 | Transformer + R-Drop | BLEU score | 30.91 | — | Unverified |
| 7 | Bi-SimCut | BLEU score | 30.78 | — | Unverified |
| 8 | BERT-fused NMT | BLEU score | 30.75 | — | Unverified |
| 9 | Data Diversification - Transformer | BLEU score | 30.7 | — | Unverified |
| 10 | SimCut | BLEU score | 30.56 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | Transformer+BT (ADMIN init) | BLEU score | 46.4 | — | Unverified |
| 2 | Noisy back-translation | BLEU score | 45.6 | — | Unverified |
| 3 | mRASP+Fine-Tune | BLEU score | 44.3 | — | Unverified |
| 4 | Transformer + R-Drop | BLEU score | 43.95 | — | Unverified |
| 5 | Transformer (ADMIN init) | BLEU score | 43.8 | — | Unverified |
| 6 | Admin | BLEU score | 43.8 | — | Unverified |
| 7 | BERT-fused NMT | BLEU score | 43.78 | — | Unverified |
| 8 | MUSE(Paralllel Multi-scale Attention) | BLEU score | 43.5 | — | Unverified |
| 9 | T5 | BLEU score | 43.4 | — | Unverified |
| 10 | Local Joint Self-attention | BLEU score | 43.3 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | PiNMT | BLEU score | 40.43 | — | Unverified |
| 2 | BiBERT | BLEU score | 38.61 | — | Unverified |
| 3 | Bi-SimCut | BLEU score | 38.37 | — | Unverified |
| 4 | Cutoff + Relaxed Attention + LM | BLEU score | 37.96 | — | Unverified |
| 5 | DRDA | BLEU score | 37.95 | — | Unverified |
| 6 | Transformer + R-Drop + Cutoff | BLEU score | 37.9 | — | Unverified |
| 7 | SimCut | BLEU score | 37.81 | — | Unverified |
| 8 | Cutoff+Knee | BLEU score | 37.78 | — | Unverified |
| 9 | Cutoff | BLEU score | 37.6 | — | Unverified |
| 10 | CipherDAug | BLEU score | 37.53 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | HWTSC-Teacher-Sim | Score | 19.97 | — | Unverified |
| 2 | MS-COMET-22 | Score | 19.89 | — | Unverified |
| 3 | MS-COMET-QE-22 | Score | 19.76 | — | Unverified |
| 4 | KG-BERTScore | Score | 17.28 | — | Unverified |
| 5 | metricx_xl_DA_2019 | Score | 17.17 | — | Unverified |
| 6 | COMET-QE | Score | 16.8 | — | Unverified |
| 7 | COMET-22 | Score | 16.31 | — | Unverified |
| 8 | UniTE-src | Score | 15.68 | — | Unverified |
| 9 | UniTE-ref | Score | 15.38 | — | Unverified |
| 10 | metricx_xxl_DA_2019 | Score | 15.24 | — | Unverified |