Manage TAR Projects

ADDAutomated Digital Discovery Review’s Technology-Assisted Review (TARTechnology Assisted Review) is based on Ipro Intelligence and Ipro Eclipse Analytics. These advanced technologies provide a computer-learning process regarding document responsiveness that can help your firm improve review accuracy and lower review costs and risks.

Particularly beneficial for cases with large document sets, TAR combines with human expertise to allow documents to be classified more efficiently and accurately than with a human-only review.

TAR project management is straightforward. After a project is created, Eclipse automatically creates all of the components needed for the TAR document evaluation, thus providing a streamlined review workflow process. TAR-specific components that are created include:

  • Advanced searches

  • Review Passes

  • Tags

  • Coding form

  • Fields

  • Reports

Related pages:

Workflow Process

A TAR project includes three review phases, as explained in the following table. The flowchart below shows the basic workflow for a TAR project.

ClosedTAR Project Phases

Round

Description

Training

The training set is based on an Ipro Intelligence search on the cluster selected for the TAR project. This search finds the documents required for review in order to train ADD Review for TAR.

Reviewers will assess these documents and tag them with TAR document tags (Responsive, Non Responsive, and optionally Do Not Use as Example).

Note: After the TAR project has been saved, documents that have already been coded during manual review can be used to expedite the time it takes to train the system.

Validation

After reviewers have evaluated the TAR project’s training set documents, several random-sample sets of remaining documents must be reviewed to verify existing system decisions and add further examples of each category. Note:

  • Validation set documents are based on a search of documents in the selected Analytics Index that have not yet been reviewed (tagged with TAR tags).

  • This is an iterative process with the goal of teaching TAR so that a human expert consistently agrees with the decisions made by the TAR system regarding document responsiveness.

Certification

A certification review is optional. It is used when the goal of TAR is to limit the number of documents to be reviewed by humans (documents found to be Non Responsive will not be reviewed). Alternatively, a final review of all documents, such as a prioritization review, might be held for remaining documents.