slate® qmt™ engine – a ready-made quantum machine translation engine to import and use immediately in slate® connect, slate® desktop, and slate® desktop pro.
| Engine Name | et-en-ep7_20191011g |
| Subject/specialty | Broad subject range, informative tone |
| Source language | Estonian (et) |
| Target language | English (en) |
| BLEU score | 47.34002 |
| Quality quotient (QQ) | 8.1% |
| Edit distance per line (Levenshtein) | 47.2 |
| Evaluation Set (free download) | 2,369 segment pairs |
| BLEU 1.0 segments (count) | 187 |
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_20191011g |
| Source/target pairs (count) | 179,498 |
| Lexicon, source language (words) | 140,365 |
| Words, source language (total) | 2,536,674 |
| Lexicon, target language (words) | 41,158 |
| Words, target language (total) | 3,411,145 |
| Monolingual Training Corpus | ep7_20191011g |
| Target segments (count) | 190,719 |
| Lexicon, target language (words) | 43,588 |
| Words, target language (total) | 3,860,170 |
| Source | EuroParl v7.0 |
| Total segment pairs | 651,746 |