Now when you log into Re:infer, you'll be redirected to a new domain that is entirely specific to your company, in the format: [company name].reinfer.io.
This won't change how you use Re:infer currently, but paves the way for additional features and functionality in future, including allowing users to create their own organisations (soon to be projects) within their domain.
We're proud to reveal a completely new model for all trainable entities. You can expect better accuracy, faster training, better validation statistics, and many exciting opportunities for fine-grained entities in the future!
Our new entity model is built on a transformer-based architecture - a type of deep learning that learns to only pay attention to the most relevant parts of an input.
We've massively improved our capabilities for filtering by label predictions. You can now apply multiple label filters at once, exclude certain labels with a filter, search with label filters, and more!
This major update coincides with some closely linked improvements in Explore and Reports for selecting labels to train and choosing which labels appear on charts.
The new Re:infer Model Rating is a game-changer for understanding and improving the performance of your models. It combines an assessment of four key performance criteria to create a holistic view of how your model is performing overall.
The Model Rating also leverages our 'next best action' recommendations to guide users on the optimal ways to improve their models in each area.
Re:infer now supports datasets and sources containing multiple European languages - no translation required!
Users can now train machine learning models on data that contains a mix of different European languages, even within the same conversation. We’ll consistently be adding to the number of languages we support, so watch this space!
If you have the necessary permissions, you can now delete verbatims from Re:infer data sources through the platform's UI.
This functionality has been available through the Re:infer API, but now lets users quickly delete unwanted verbatims with a few clicks!