AI vs. The Eye: 5 Common Questions About Technology-Assisted Review | Array

AI vs. The Eye: 5 Common Questions About Technology-Assisted Review | Array

  • Technology
  • May 23, 2022
  • No Comment
  • 66
  • 5 minutes read


Advances in artificial intelligence, including predictive coding and continuous machine learning, are creating opportunities to make eDiscovery more efficient and effective.

However, according to the eDiscovery Today 2022 Industry Status Report, a minority (25.9 percent) of active eDiscovery professionals surveyed said they use predictive coding technology in all or most of their cases. Of those surveyed, 36.3% said they use it in very few or none of their cases.

This disconnect is likely to come from the lack of convenience with the confidence in technology to do the job of removing potentially sensitive records. Over the last decade, new technologies driven by artificial intelligence have gained ground in terms of use and acceptance.

Here are five common questions about using AI in eDiscovery.

What is ART?

TAR stands for Technology-Assisted Review. There are two generations of ART, commonly called ART 1.0 and ART 2.0.

What is TAR 1.0?

TAR 1.0 is commonly known as sample-based learning. Represents the first generation of TAR systems.

In TAR 1.0, teams involved in eDiscovery extracted samples of documents from a larger batch, reviewed them, and marked them as responsive or not to the discovery request.

They would then feed the sample documents to the predictive coding software, basically teaching the computer what to look for in the responsive documents and delete the unresponsive documents. Under this approach, the document review teams had to remove several sample populations and stop and start the process to test the accuracy and further refine the model based on the results of each sample.

How is TAR 2.0 different from TAR 1.0?

Today, TAR 2.0 is considered the standard form of technology-assisted review. It is based on continuous active learning. In TAR 2.0, computers still rely on samples to provide coding decisions to the algorithm, but these samples are now generated automatically, and instead of pre-selecting them, the computer selects the sample documents that will have the most impact. great at teaching the system how to differentiate between responsive and non-responsive documents. As humans are encoding more documents and introducing them into the software, the system, in the background, is continually learning and updating their understanding of what makes a document respond.

The clear advantage of TAR 2.0 is that the revision process is much smoother, requires fewer stops and starts, and tends to result in a stabilized model long before the process.

Where does TAR 2.0 shine?

TAR 2.0 is great for quickly deleting unanswered documents. It does this especially well for sorting different information into separate “responsive” and “unresponsive” repositories. However, systems can struggle with this nuance. For example, if a team is reviewing documents in a lawsuit that includes bakery products, the computer may be good at figuring out the difference between cupcakes and spaghetti, but it is difficult to differentiate responsive documents on cupcakes made from white cupcake flour. made with wheat flour. .

Does ART replace the need for human review?

Using TAR 2.0 in your eDiscovery review process can significantly reduce the workforce needed to potentially review thousands of documents and determine their responsiveness.

Teams can use it to immediately reduce the set of responsive documents and have their teams review the responsive documents. They can also use TAR 2.0 along with search terms to focus even more on what interests them most in litigation.

After all, legal teams still have to review the records of privileged materials and know what they are producing, so that humans have a role to play in the technology-assisted review process.

If you are unsure whether the AI ​​is right for your project, it may be helpful to hire an eDiscovery provider who knows the technology. Working with an eDiscovery provider at the beginning of a project can help you finish your eDiscovery project more efficiently and help you keep costs down.



Source link

Related post

EDUCAUSE 2022: How Data Collection Can Improve Student and Faculty IT Support

EDUCAUSE 2022: How Data Collection Can Improve Student and…

At Indiana University, Gladdin said, to make life easier for students and faculty, they implemented a course template for the Canvas…
UGC, AICTE warn students against online PhD programmes offered by EdTech platforms | Latest News India

UGC, AICTE warn students against online PhD programmes offered…

The University Grants Commission (UGC) and the All India Council for Technical Education (AICTE) on Friday issued a joint advisory against…
UGC, AICTE warn students against online PhD programmes offered by EdTech platforms | Latest News India

UGC, AICTE warn students against online PhD programmes offered…

The University Grants Commission (UGC) and the All India Council for Technical Education (AICTE) on Friday issued a joint advisory against…

Leave a Reply

Your email address will not be published.