Skip to content

Adding "SignBLEU: Automatic Evaluation of Multi-channel Sign Language Translation" and some eval metrics discussion #77

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

Conversation

cleong110
Copy link
Contributor

@cleong110 cleong110 commented Jun 12, 2024

cleong110#21 details and checklist

@cleong110
Copy link
Contributor Author

cleong110 commented Jun 14, 2024

All right, I think we're about ready for review:

https://chatgpt.com/share/2a913f6c-e344-4a00-86ab-357bbae6ec8d is the conversation with ChatGPT and revisions of the summary. Took some, discarded others

Questions:

  • Do we need to include more detail about the human review process, ethics, etc.?
  • How's the use of simple past tense? Style guide talks about this, but unsure whether I ought to say "introduce" or "introduced.
  • Do we have a policy of "analyse" vs "analyze"?

@cleong110 cleong110 marked this pull request as ready for review June 14, 2024 20:23
@cleong110 cleong110 changed the title (DRAFT) Adding "SignBLEU: Automatic Evaluation of Multi-channel Sign Language Translation" Adding "SignBLEU: Automatic Evaluation of Multi-channel Sign Language Translation" Jun 14, 2024
@cleong110
Copy link
Contributor Author

Added some more detail on pose output metrics, and some citations for APE

@cleong110 cleong110 requested a review from AmitMY June 19, 2024 18:39
@cleong110 cleong110 changed the title Adding "SignBLEU: Automatic Evaluation of Multi-channel Sign Language Translation" Adding "SignBLEU: Automatic Evaluation of Multi-channel Sign Language Translation" and some eval metrics discussion Jun 19, 2024
src/index.md Outdated
Naively, works in this domain have used metrics such as mean squared error (MSE) or Average Position Error (APE) for pose outputs [ahuja2019Language2PoseNaturalLanguage;ghosh2021SynthesisCompositionalAnimations;petrovich2022TEMOSGeneratingDiverse].
However, these metrics have significant limitations for Sign Language Production.

For example, MSE and APE do not account for variations in sequence length, for cases where where the same sign might take different amounts of time to produce.
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

where where
"different amounts of time" sounds strange to me

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

How about:

For example, MSE and APE do not account for variations in sequence length.
The same sign may not always take exactly the same amount of time to produce.

Or various options here: https://chatgpt.com/share/e4e5cde3-fccf-4e40-ab2f-5b210db6cf6f

@AmitMY AmitMY merged commit 5d7dead into sign-language-processing:master Jun 21, 2024
1 check failed
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

Successfully merging this pull request may close these issues.

2 participants