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-hu-ep7_20191011j |
Subject/specialty | Broad subject range, informative tone |
Source language | English (en) |
Target language | Hungarian (hu) |
BLEU score | 38.93057 |
Quality quotient (QQ) | 5.0% |
Edit distance per line (Levenshtein) | 56.4 |
Evaluation Set (free download) | 2,370 segment pairs |
BLEU 1.0 segments (count) | 121 |
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_20191011j |
Source/target pairs (count) | 185,291 |
Lexicon, source language (words) | 41,818 |
Words, source language (total) | 3,636,418 |
Lexicon, target language (words) | 153,148 |
Words, target language (total) | 3,050,993 |
Monolingual Training Corpus | ep7_20191011j |
Target segments (count) | 202,860 |
Lexicon, target language (words) | 170,095 |
Words, target language (total) | 3,690,633 |
Source | EuroParl v7.0 |
Total segment pairs | 624,934 |