Document AI Workbench

Uptraining means that you begin with a prebuilt ML model, and then train this model with your own data to improve its accuracy for your organization’s documents. Pre-built models offer a base model relevant to your document type and help automatically label data so you can build production ready models faster. Document AI generates evaluation metrics, such as precision and recall, to help you determine the predictive performance of your models. These evaluation metrics are generated by comparing the entities returned by the models (the predictions) against the annotations in the test documents.

Create custom extractors that are specific to your documents, and are trained and evaluated with your data for higher accuracy and performance. Once you create an initial model, use it to auto-label documents to train a production ready model faster. With a deployed model, extract structured data from documents to automate processes and unearth insights. Use generative AI to quickly improve custom models through prompts. Use this feature to deploy new models or auto-label datasets, saving time and cost. For example, quickly add a new field to your data by prompting a foundation model to add this new field to your data instead of having to label and train a new model. You can also use the same approach to auto label new datasets.

Create custom classifiers that identify a document type from a set of document classes. Classifying document types help businesses save time, effort, and money. For example, you can validate if users submit the right documents within an application. Also, you can classify documents to automate downstream processes such as choosing the best model to extract data from a document. 

Create custom splitters to split and classify multiple documents within a single file. Custom splitter helps users sort and classify documents so they can validate if they have all the needed documents from an applicant. For example, a custom splitter can classify and identify the page numbers of a driver’s license, paystub, W-2, and bank statement (and others) within a single document. Furthermore, individually classified documents enable businesses to better automate downstream processes, including selecting the proper storage, analysis, or processing steps based on the document type like data extraction. 

Use document summarizer to create summaries for both short and long documents. You can customize summaries based on your preference. For example, you can decide if you want your summaries to be long or short, paragraphs or bullet points etc. There is no model training required to access this function. However you have the ability to fine tune underlying models to improve the quality of summaries generated.