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 | en-bg-ep7_20191011a |
Subject/specialty | Broad subject range, informative tone |
Source language | English (en) |
Target language | Bulgarian (bg) |
BLEU score | 61.86316 |
Quality quotient (QQ) | 17.0% |
Edit distance per line (Levenshtein) | 31.9 |
Evaluation Set (free download) | 2,345 segment pairs |
BLEU 1.0 segments (count) | 417 |
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_20191011a |
Source/target pairs (count) | 102,444 |
Lexicon, source language (words) | 30,626 |
Words, source language (total) | 1,976,121 |
Lexicon, target language (words) | 59,360 |
Words, target language (total) | 1,878,165 |
Monolingual Training Corpus | ep7_20191011a |
Target segments (count) | 111,883 |
Lexicon, target language (words) | 64,342 |
Words, target language (total) | 2,249,831 |
Source | EuroParl v7.0 |
Total segment pairs | 406,934 |