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 | fi-en-ep7_20191011h |
Subject/specialty | Broad subject range, informative tone |
Source language | Finnish (fi) |
Target language | English (en) |
BLEU score | 41.58043 |
Quality quotient (QQ) | 7.0% |
Edit distance per line (Levenshtein) | 43.7 |
Evaluation Set (free download) | 2,379 segment pairs |
BLEU 1.0 segments (count) | 139 |
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_20191011h |
Source/target pairs (count) | 272,714 |
Lexicon, source language (words) | 197,782 |
Words, source language (total) | 3,112,215 |
Lexicon, target language (words) | 49,681 |
Words, target language (total) | 4,479,716 |
Monolingual Training Corpus | ep7_20191011h |
Target segments (count) | 282,995 |
Lexicon, target language (words) | 52,138 |
Words, target language (total) | 4,875,974 |
Source | EuroParl v7.0 |
Total segment pairs | 1,924,942 |