Overview
Quality Assurance (QA) is the second variety of Supervision tasks. These tasks occur after submissions are completed, and therefore do not affect the speed in which a submission flows through the system.
It is important to note that if an error is found during the QA Process, it will not retroactively change the output of the specific field.
Quality Assurance
Quality Assurance tasks serve two important purposes:
QA measures the accuracy of the machine and human at both an aggregated and individual keyer level. For more information on how accuracy is determined, see articles Scoring Transcription Accuracy and Scoring Field Identification Accuracy.
QA gathers data to continuously improve various machine learning models and helps the system to deliver more accurate results over time. This is especially important for Semi-structured documents.
Below is a list of all the QA tasks that a user can complete. See the corresponding links for more information on how to complete each task.
Ordering of Quality Assurance tasks
QA tasks for the newest submissions are presented first. Having keyers complete QA tasks for the most current submissions ensures that the obtained QA data is as relevant as possible.