diff options
author | TharinduDR <rhtdranasinghe@gmail.com> | 2020-10-13 18:12:35 +0300 |
---|---|---|
committer | TharinduDR <rhtdranasinghe@gmail.com> | 2020-10-13 18:12:35 +0300 |
commit | d469d793e37fc4983df2997b4bccc0a4782bd6fb (patch) | |
tree | 71e568180916464bc8aa66e2cf5f75647a56c001 /docs | |
parent | e26a3ccc83d590bf27eb3d7f4a2463b04eb9e765 (diff) |
033: Adding documentation
Diffstat (limited to 'docs')
-rw-r--r-- | docs/pretrained.md | 6 |
1 files changed, 4 insertions, 2 deletions
diff --git a/docs/pretrained.md b/docs/pretrained.md index 25468a3..372cd1a 100644 --- a/docs/pretrained.md +++ b/docs/pretrained.md @@ -29,7 +29,8 @@ We have released several quality estimation models for this aspect. We have also | \*-\* | Any | Any | MonoTransQuest | | | | | | SiameseTransQuest | | - +!!! note +\* denotes any language. (\*-\* means any language to any language) ## Predicting Direct Assessment The current practice in MT evaluation is the so-called Direct Assessment (DA) of MT quality, where raters evaluate the machine translation on a continuous 1-100 scale. This method has been shown to improve the reproducibility of manual evaluation and to provide a more reliable gold standard for automatic evaluation metrics @@ -61,4 +62,5 @@ We have released several quality estimation models for this aspect. We have also | \*-\* | Any | Any | MonoTransQuest | | | | | | SiameseTransQuest | | - +!!! note +\* denotes any language. (\*-\* means any language to any language) |