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-fr-ep7_20191011i |
Subject/specialty | Broad subject range, informative tone |
Source language | English (en) |
Target language | French (fr) |
BLEU score | 50.73097 |
Quality quotient (QQ) | 10.0% |
Edit distance per line (Levenshtein) | 39.1 |
Evaluation Set (free download) | 2,367 segment pairs |
BLEU 1.0 segments (count) | 249 |
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_20191011i |
Source/target pairs (count) | 173,342 |
Lexicon, source language (words) | 37,399 |
Words, source language (total) | 2,768,761 |
Lexicon, target language (words) | 46,886 |
Words, target language (total) | 3,130,992 |
Monolingual Training Corpus | ep7_20191011i |
Target segments (count) | 183,684 |
Lexicon, target language (words) | 49,407 |
Words, target language (total) | 3,544,900 |
Source | EuroParl v7.0 |
Total segment pairs | 2,007,723 |