Add FLORES+ multilingual translation tasks and common configuration#3920
Open
djstrong wants to merge 4 commits into
Open
Add FLORES+ multilingual translation tasks and common configuration#3920djstrong wants to merge 4 commits into
djstrong wants to merge 4 commits into
Conversation
- Introduced a new task set for FLORES+ that includes various translation tasks from English to multiple languages, enhancing the multilingual capabilities of the evaluation framework. - Added a common YAML configuration file for FLORES+ tasks to standardize settings such as metrics and generation parameters. - Updated the README to include the new FLORES+ task information, ensuring users are aware of the available multilingual translation options. This update expands the task offerings and improves usability for multilingual evaluations.
This commit deletes multiple YAML files related to FLORES+ translation tasks, which are no longer needed. The removed files included various language pairs for English to other languages, streamlining the task set and improving maintainability. No functional changes were made to the remaining codebase.
This commit introduces multiple YAML files for FLORES+ translation tasks, covering a wide range of language pairs from English to various languages. Each task includes specific instructions for translation, enhancing the multilingual capabilities of the evaluation framework. This update expands the task offerings and improves usability for multilingual evaluations.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
This update expands the task offerings and improves usability for multilingual evaluations.
I tested it on one pair of languages:
As there is 400 000 pairs of languages I only included translation task from English to any other language.
The dataset is gated - is it a problem?