This package contains a ready-made Quantum Machine Translation™ (QMT™) engine to import and immediately use in Slate Desktop™, Slate Desktop Pro™ and Slate Connect™.
| Engine Name | de-en-ep7_20191011d |
| Subject/specialty | Generic, parliament debates |
| Source language | German (de) |
| Target language | English (en) |
| BLEU score | 47.29717 |
| Quality quotient (QQ) | 9.4% |
| Edit distance per line (Levenshtein) | 39.0 |
| Evaluation segments (count) | 2,363 |
| BLEU 1.0 segments (count) | 225 |
| Evaluation set (free download) | Download Free |
Training Resources
This package includes the engine’s training corpus. We used the QMT strategy to create the smallest possible training corpus that maximizes machine translation post-editing productivity.
| Parallel Training Corpus | ep7_20191011d |
| Source/target pairs (count) | 156,261 |
| Lexicon, source language (words) | 70,968 |
| Words, source language (total) | 2,399,586 |
| Lexicon, target language (words) | 39,734 |
| Words, target language (total) | 2,569,289 |
| Monolingual Training Corpus | ep7_20191011d |
| Target segments (count) | 163,744 |
| Lexicon, target language (words) | 42,305 |
| Words, target language (total) | 2,856,802 |
| Original EuroParl v7.0 total segment pairs | 1,920,209 |