Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Why is MT inconsistent even when context is clear #80

Closed
SafeTex opened this issue Jun 30, 2023 · 1 comment
Closed

Why is MT inconsistent even when context is clear #80

SafeTex opened this issue Jun 30, 2023 · 1 comment

Comments

@SafeTex
Copy link

SafeTex commented Jun 30, 2023

Hello Tommi and all

I'd like to know why MT is so inconsistent, even when context is super clear, as in

image

I mean, Opus got the first occurrence "Menscykel" wrong and then got it right in the very next sentence.

Is this down to the capital letter again? I'm already running your regex to convert uppercase to lowercase but not where the first letter only is capitalized.

I'm now wondering if I should make everything lowercase?

@TommiNieminen
Copy link
Collaborator

In this case, the problem is probably the Markdown bold formatting (the double asterisks around the segment). If I remove the asterisks, the translations get better:

image

You could fix the problem either by using a pre-edit rule to strip markdown formatting before generating the MT, or preferably by using a Markdown file type in Studio (there is one, I think, although I haven't tested it), so that the Markdown formatting is shown as tags instead of plain text.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants