Teach your AI to fit your solve your information extraction task.
Powered by active learning, automatic machine learning, and in-house foundation models.
Automatically assign a class (a.k.a. label) to a text document. You teach the model how to predict the correct class from a custom set of classes (e.g. âBiologyâ and âPhysicsâ) that you define during the teaching process. Great for sentiment analysis, content moderation, or topic identification.
Automatically assign a set of labels to a text document. Each document can be given one label, multiple labels, or no label at all. It can be used for topic classification when multiple topics can be present in the same document.
Identify and classify any kind of entities or concepts mentioned in a text document. You teach the model how to recognize entities from a custom set of entity types (e.g. âPersonâ or âAddressâ) that you define during the teaching process. Entity Detection can also be used to extract paragraph-length spans.
Drastically reduce the amount of labels necessary by building on top of large language models.
Analyze large volumes of data using topic modeling to understand, extract themes, and categorize documents effectively.
Speed-up labeling by letting the model identify the most informative documents.
Transform text into JSON. Extract all kinds of information from a document - entities, quantities, dates, and so on - and identify their (potentially hierarchical) relationships. The extracted information is structured in the form of a tree which follows a template (a.k.a. schema).
.png)
