For example, the phrase, \u201crun over the hill and attack\u201d used in a game would be considered a medium level of violence and blocked if the gaming system was configured to block medium severity content. An adjustment to accept medium levels of violence would enable the model to tolerate the phrase.<\/p>\n<\/blockquote>\n

\u201cWe have a team of linguistic and fairness experts that worked to define the guidelines taking into account cultural, language and context,\u201d a Microsoft spokesperson added. \u201cWe then trained the AI models to reflect these guidelines \u2026 AI will always make some mistakes, [however,] so for applications that require errors to be nearly non-existent we recommend using a human-in-the-loop to verify results.\u201d<\/p>\n

One early adopter of Azure AI Content Safety is Koo, a Bangalore, India-based blogging platform with a user base that speaks over 20 languages. Microsoft says it\u2019s partnering with Koo to tackle moderation challenges like analyzing memes and learning the colloquial nuances in languages other than English.<\/p>\n

We weren\u2019t offered the chance to test Azure AI Content Safety ahead of its release, and Microsoft didn\u2019t answer questions about its annotation or bias mitigation approaches. But rest assured we\u2019ll be watching closely to see how Azure AI Content Safety performs in the wild.<\/p>\n