Training Models

Training Models

Training Data Management Features

Training Data Management (formerly Keyer Data Management) includes tools for controlling and managing Identification model performance. The performance of your models depends on the quality of the pages, the diversity of the documents, and ...

Document Eligibility Filtering

Document Eligibility Filtering indicates whether a document is eligible for training, based on internal checks in the application and our machine learning logic. It provides additional information about documents that were excluded from the training...

Training Data Curator

Having a diverse, representative training set is crucial for a high-quality identification model. In v37, the Hyperscience application allows you to train a model with fewer annotations with minimal impact on performance.  How data is curated...

Detecting and Correcting Anomalies in Table Annotations

A high-quality model requires consistent annotations. That's why the Hyperscience application has a tool, called Labeling Anomaly Detection, for identifying potential discrepancies in the training datasets before running model training. Once the ann...

Detecting and Correcting Anomalies in Field Annotations

Even if all your keyers go through the same training in annotating fields for a given use case, they may not always annotate the same fields consistently. Inconsistencies in annotations can impact model performance, and finding the cause of the redu...

Retraining Existing Models

Retraining a Field or Table ID model is not necessary if one, or some combination, of the following properties were changed in an existing field’s settings: Field name Output name Supervision Required Identification Supervisi...

Training a Classification Model

To achieve better automation rates for document classification, a classification model must be trained for each Semi-structured and Additional layout. Training a Classification Model How to Initially Train the Classification Model To train a n...

Forward-Compatible Models

In v38, models for flows created in v36 and above are forward compatible , meaning that you can use them in v38 without having to retrain them during the upgrade process. As a result, forward-compatible models allow you to: upgrade v36 or v37...

Managing Transcription Models

The features available in the Model Library ( Library > Models ) allow you to manage your finetuning models. From the Model Library, you can: deploy a more performant version of a model, check the progress of a finetuning model’s...

Model Management

Overview In Hyperscience, model management takes place within Library > Models . From here you can see a table that displays a list of Semi-structured layouts and their associated models. In this table, you can see the state of the m...

Training a New Field Identification Model

There are two ways to train a Field ID model. To manually train and deploy models, go to the Model Details page, and follow the instructions in this article. To automatically train and deploy Field ID models, you can enable the Continuous Fie...

Training a New Table Identification Model

A trained Table ID model enables cell-level predictions and automatic table processing. A Table ID model can be trained to automatically identify both gridded and non-gridded tables. A standard grid format refers to tables where data falls neat...

Requirements for Training a New Model

Overview If you create a new Semi-structured layout version, there will be no models immediately available. For optimal layout performance, train a model on the newest layout version. Recall that identification models are trained at the layout lev...

Evaluating Model Training Results

Overview Once a new Field ID or Table ID model is trained or uploaded, before uploading the model, you can evaluate the projected automation based on the Field Identification Target Accuracy setting for Field ID models and Table Identification...

Training Data Analysis and Guided Data Labeling

Overview The Training Data Analysis (previously known as Keyer Data Management or KDM) feature allows you to reduce the number of annotation errors and makes the process of training Field Locator and Table Locator models faster and less complex....

Training Data Management

With our Training Data Management tools, you can: View field and table locator models’ training data. View and edit ground-truth data for locator models. View a list of documents used to train a locator model. Choose whether to ...

Importing and Exporting Training Data

Overview To ensure that you do not lose any training data during application upgrades and model setups, you can move your training data between environments. The ability to export your models’ training data from production to lower environments ...

Model Compatibility Logic

Overview Each model is only compatible with one Semi-structured layout, but a model is not necessarily compatible with every version of a layout. Compatibility logic is determined by comparing fields that the model was trained on (e.g. fields in t...

Canceling or Retrying a Training Job

Overview To take action on Field Locator model training, or any training job for that matter, navigate to Administration > Trainer . To learn more about the Trainer application, see  What is the Trainer? Canceling a training job Fol...

Managing Transcription Models Across Flows

To meet the specific automation needs of your various lines of business, you can configure transcription, or finetuning, models at the flow level. This flexibility allows you to: enter dedicated transcription automation and accuracy setting...