Bumble Tech
Published in

Bumble Tech

Multilingual message content moderation at scale

Part 1: introduction, model’s design and production infrastructure

When a member receives a message within our app that could be harmful or hurtful to the reader, thanks to the model we’re able to check in with the member in real-time through a pop-up message

Transformers-based architectures and Foundation models

A Transformer composed of two stacked encoders and decoders. Thanks to Alammar, J (2018). The Illustrated Transformer [Blog post]. Retrieved from https://jalammar.github.io/illustrated-transformer/

Design and multilingual validation

Production infrastructure and business impact

Simplified architecture of the internal deep learning inference service.
A naive Tensorflow implementation of the tokeniser is required by XLM-Roberta. It is very similar to Sentencepiece but requires additional work around some tokens

Conclusion and next steps



Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store