Adding a "context" option to improve translation quality and avoid Gender Bias

Tony O'Hagan 0 Reputation points
2024-08-28T00:39:37.71+00:00

This really feedback to the Azure Translator team ...

I've observed that when translating from English to a gender specific language like French or Hindi the translation result can have a bias towards translating text from a male perspective rather than female. I see that Bing Translate has sought to address this by showing both male and female translations so I think the engine has the capability but I can understand that this is constrained by the current API. What's missing is the translation "context" so one approach that I might address this and improve translation would be to introduce a translation "context" option. This is the solution that I see DeepL has added that I suspect would be the most beneficial:

Azure Translator
Azure Translator
An Azure service to easily conduct machine translation with a simple REST API call.
388 questions
{count} votes

1 answer

Sort by: Most helpful
  1. navba-MSFT 23,620 Reputation points Microsoft Employee
    2024-08-28T03:02:24.7166667+00:00

    @Tony O'Hagan Welcome to Microsoft Q&A Forum, Thank you for posting your query here!

    .

    Thanks for sharing your valuable feedback for Azure Translator. Please post this feedback and feature-requests in the Azure Cognitive Services feedback forum, so that it can be monitored and tracked by the Product Owners:

    https://feedback.azure.com/d365community/forum/09041fae-0b25-ec11-b6e6-000d3a4f0858

    Also users having similar ask or feature request can upvote your idea on that forum.

    .

    .

    Hope this helps. If you have any follow-up questions, please let me know. I would be happy to help.

    **

    Please do not forget to "Accept the answer” and “up-vote” wherever the information provided helps you, this can be beneficial to other community members.

    0 comments No comments

Your answer

Answers can be marked as Accepted Answers by the question author, which helps users to know the answer solved the author's problem.