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-it-ep7_20191011k |
Subject/specialty | Broad subject range, informative tone |
Source language | English (en) |
Target language | Italian (it) |
BLEU score | 48.03313 |
Quality quotient (QQ) | 9.5% |
Edit distance per line (Levenshtein) | 40.7 |
Evaluation Set (free download) | 2,358 segment pairs |
BLEU 1.0 segments (count) | 217 |
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_20191011k |
Source/target pairs (count) | 137,886 |
Lexicon, source language (words) | 36,482 |
Words, source language (total) | 2,252,459 |
Lexicon, target language (words) | 51,763 |
Words, target language (total) | 2,220,407 |
Monolingual Training Corpus | ep7_20191011k |
Target segments (count) | 145,817 |
Lexicon, target language (words) | 55,299 |
Words, target language (total) | 2,515,584 |
Source | EuroParl v7.0 |
Total segment pairs | 1,909,115 |