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 | el-en-ep7_20191011e |
Subject/specialty | Broad subject range, informative tone |
Source language | Greek (el) |
Target language | English (en) |
BLEU score | 52.81056 |
Quality quotient (QQ) | 13.0% |
Edit distance per line (Levenshtein) | 36.2 |
Evaluation Set (free download) | 2,366 segment pairs |
BLEU 1.0 segments (count) | 308 |
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_20191011e |
Source/target pairs (count) | 169,400 |
Lexicon, source language (words) | 83,423 |
Words, source language (total) | 2,933,084 |
Lexicon, target language (words) | 42,071 |
Words, target language (total) | 2,978,493 |
Monolingual Training Corpus | ep7_20191011e |
Target segments (count) | 181,123 |
Lexicon, target language (words) | 45,707 |
Words, target language (total) | 3,434,775 |
Source | EuroParl v7.0 |
Total segment pairs | 1,235,976 |