https://platform.instabase.com/docs/26.04/extract-classify/index.html Recent content in Extract and classify documents on Instabase Platform Documentation Hugo -- gohugo.io en-us https://platform.instabase.com/docs/26.04/extract-classify/about-ml-studio/index.html Mon, 01 Jan 0001 00:00:00 +0000 https://platform.instabase.com/docs/26.04/extract-classify/about-ml-studio/index.html Machine Learning Studio uses deep learning models to enable document understanding. With ML Studio, you annotate sample documents and evaluate and train deep learning models. The models you develop in ML Studio form a key piece of most Instabase solutions. Models are responsible for classifying documents and extracting data. Model development begins with annotation, which demonstrates how you want documents to be classified and what data you want extracted. You then use the annotation set to evaluate and train models. https://platform.instabase.com/docs/26.04/extract-classify/ibformers/index.html Mon, 01 Jan 0001 00:00:00 +0000 https://platform.instabase.com/docs/26.04/extract-classify/ibformers/index.html Table of Contents Dependency compatibility Upgrade published models ibformers documentation Base models Update Marketplace ML Studio relies on training scripts, in the form of an ibformers package, and base models. Both of these dependencies are provided through the Marketplace and must be updated periodically. For new Instabase installations, ML Studio dependencies are typically installed through automated post-install actions, and no further action is required. For upgrades to version 23.01 or later, you must update Marketplace to make available the latest ibformers files and base models. https://platform.instabase.com/docs/26.04/extract-classify/annotation/index.html Mon, 01 Jan 0001 00:00:00 +0000 https://platform.instabase.com/docs/26.04/extract-classify/annotation/index.html Table of Contents Annotation set settings Model training requirements for annotation sets Creating classes and schemas Modifying schemas Assigning classes Annotating fields Annotating text Annotating multiple instances of the same value Annotating a list of different values Annotating tables Redigitizing documents Using annotation assist Manually selecting test records Exporting annotation sets Creating annotation sets based on human review Annotation statuses Annotation sets demonstrate how you want documents to be classified and what data you want extracted. https://platform.instabase.com/docs/26.04/extract-classify/model-training/index.html Mon, 01 Jan 0001 00:00:00 +0000 https://platform.instabase.com/docs/26.04/extract-classify/model-training/index.html Table of Contents Marketplace models vs. base models Importing and evaluating Marketplace models Training requirements for annotation sets Model training options Model types Selecting a model Test / train split Hyperparameters Assessing model performance Metrics Configuration Test records Logs Pruning models Publishing models Importing legacy models Model training teaches an existing deep learning model how to process documents that are representative of those the model will encounter in your production environment. https://platform.instabase.com/docs/26.04/extract-classify/refiner/index.html Mon, 01 Jan 0001 00:00:00 +0000 https://platform.instabase.com/docs/26.04/extract-classify/refiner/index.html Use Refiner to clean and format data extracted using ML Studio, or to programmatically extract data directly from documents. About RefinerWork with documents directly to extract text and visual information. Refiner language grammarRefiner language grammar and syntax rules. Measure accuracy with Target ComparisonMeasure text field extraction accuracy as you build and make incremental changes in Refiner. Scan BoxExtract content from a box. Provenance TrackingProvenance tracking in Refiner functions and UDFs determine where some output came from within its input. https://platform.instabase.com/docs/26.04/extract-classify/validations/index.html Mon, 01 Jan 0001 00:00:00 +0000 https://platform.instabase.com/docs/26.04/extract-classify/validations/index.html Table of Contents Creating a validation module from Flow Creating a validation module from the Validations app Configuring a validation Associate data with a validation Configuring rules and conditions Create a rule Add conditions to rule Validation conditions Type Validation condition Confidence Threshold condition Comparison condition External Code condition Writing custom functions for conditions Functions for top-level fields Functions for nested fields Configure validations and include them in your flow to ensure that data has been correctly extracted.