Discuss Technology Assisted Reviews of Data in a Document Management System

What is Technology Assisted Review?

If we are going to discuss Technology Assisted Review, or TAR, we should commencement at the beginning.

"Electronically stored information", or "ESI", is data that is stored in electronic course. Electronic discovery, or eDiscovery, is nigh what we do with ESI.

Stepping dorsum a little, a lawsuit or investigation almost e'er is the outgrowth of i or more than events where 1 or more people did something. Lawyers and investigators need to locate - or "discover" - data virtually those events, those people. They need this information for 3 basic reasons. First, they apply it to figure out what appears to have happened. Second, they utilise ESI to help build that stories they need to tell, their explanations of what happened, every bit well every bit to counter the stories told past other such equally opposing counsel. Third, they generally need to produce some portion of the ESI to others such as other litigants or regulatory agencies.

Often, this process is described as "finding relevant documents". The data they need to discover takes one of four forms:

• Information stored in electronic form. This is ESI. ESI is anything stored on a reckoner, on a mobile device, on a corporate network, in the cloud. It covers all files types. Email typically accounts for the largest number of files, merely eDiscovery processing tools typically work with hundreds of file types. Reveal Processing, for example, can process over 900 different file types.
• Data in people's heads. This information is gathered by talking with people - chatting with them informally; interviewing them; or asking them questions during depositions, at hearings, at trials, or in other situations where they are under adjuration to tell the truth. Information gathered from people'south head mattered then and it matters today.
• Information stored on paper. Information stored on paper or similar media such as microfilm used to be one of two main sources of information lawyers and investigators turned to discover out what happened (the other was, and still is, information in people's heads). Sometimes we only had to leafage through the contents of a single manila folder. Other times we had to scour the contents of unabridged warehouses. Today, even so, information on paper by and large is a minuscule amount of what nosotros deal with.
• Information stored in tangible objects. For some matters, you need to examine concrete things. I used to piece of work on all-terrain vehicle, snowmobile and motorcycle cases, and for those we most e'er wanted to see the actual vehicle involved in the alleged event. In ane notable lawsuit, the investigator chosen me to say, "Y'all aren't going to believe this, but they sued the wrong visitor. Someone else's nameplate is on the gasoline tank!"

ESI inverse everything. Even a small matter tin can involve a million messages. Big matters hands run to 10s or even 100s of millions of files. With this explosion in the volume of data we need to deal with, mere manual review no longer was enough.

And so Came Technology Assisted Review

Artificial intelligence came to the rescue.

TAR is a process of having computer software electronically classify documents based on input from expert reviewers, in an effort to expedite the organization and prioritization of the document collection.

"Technology Assisted Review", or "TAR", is one of several names the legal industry uses for a blazon of artificial intelligence chosen "supervised machine learning". TAR is, per theEDRM website, "a process of having figurer software electronically classify documents based on input from proficient reviewers, in an endeavor to expedite the system and prioritization of the certificate collection."

Typically, TAR is deployed in lawsuits and investigations to aid discover ESI of involvement or for alternative out ESI that is deemed not worthy of further consideration. Other names for TAR include "predictive coding" and "computer assisted review".

TAR can be used in addition to or to a certain extent in identify of "search terms" - specific words that are hoped will identify responsive documents. Information technology likewise tin can exist used to reduce the amount of manual review required to become through a dataset, reducing the number of documents on which reviewers need to lay optics.

Nosotros discussed machine learning in greater detail in an earlier post, Legal AI Software: Taking Document Review to the Next Level. Modern machine learning dates back to the mid-twentieth century. It focuses "on developing programs that teach computers to change when exposed to new information and to grow. Its goal is to empathize and follow the methods by using algorithms to do that chore automatically without whatsoever human being aid."

For our purposes today, automobile learning takes two forms, unsupervised and supervised. Both are forms of categorization, ways to sort documents into buckets such every bit "relevant" and "not relevant".

Unsupervised machine learning is, essentially, an exercise in having computers "tell me something I don't know." Computer algorithms are pointed at datasets. The algorithms organize that data based on patterns, similarities, and differences. The algorithms work on their own; they do not rely on people to train them. They can, nonetheless, learn from their own past experience.

Supervised auto learning is, equally much as annihilation else, a methodology to "find more like this." Users are actively involved in procedure. They are presented with information, such as an email message, and asked to "classify", or make a binary choice near, that information. They might be asked to decide whether all or some role of a document is relevant, or privileged, or related to an issue in the affair. The machine learning organization "learns" from that decision: If that document's contents suggested fraudulent activity, its says to itself, what similar documents tin I detect that might also propose fraudulent activity.

For most practical purposes, TAR comes in two flavors, TAR 1.0 and TAR 2.0. With both flavors, the organization presents batches of documents to review teams. Each reviewer goes through each batch 1 document at a time. The reviewer classifies each certificate, deciding whether that certificate (or some subpart of that certificate) meets a preset benchmark. Often we describe this every bit the document's "responsiveness". Some systems limit reviewers to a binary choice: yeah or no. Other systems allow the reviewer not to determine, instead skipping to the next document in the batch.

The main unlike between TAR 1.0 and TAR 2.0 is the workflow surrounding those decisions. TAR 1.0 systems are, essentially, ones designed to be trained and then set loose. TAR 1.0 starts with the creation of a specific set of documents (a "seed set" or a "command set") that reviewers will use to train the arrangement. Reviewers go through that fix until a predetermined threshold is met. Typically, arriving at that threshold is something alike to the system reaching a indicate where it says, in essence, "From the decisions you reviewers have made, I now know enough about what you are looking for that all by myself I tin become through all the remaining documents and with a high degree of confidence find all the other documents you want." Reveal offers two flavors of TAR 1.0, "COSMIC Active Learning" in Reveal AI, and "Predictive Coding" in Brainspace.

TAR 2.0 systems are designed with a different goal in mind. They are meant to help button the most interesting documents to the forepart of the line. There is no need for a seed or control set. Each reviewer starts with a batch of documents, depending on the system anywhere from x or so documents up to several hundred. Those batches might consist of randomly selected documents, or those could be documents assembled with any of a wide variety of themes in mind. After a reviewer codes all documents in the batch, that batch does back to the system. The arrangement looks at the coded information - the classifications. With that information, the system reevaluates the remaining documents. It places at the front of the line those documents near akin to the ones classified as responsive, privileged, or whatever the criterion was. So it grabs the adjacent batch of documents (10, 100, whatsoever the batch size might be), and feeds that to the reviewer. This process continues until someone decides it is time to stop.

TAR Can Assistance

Equally discussed above, past using TAR you lot tin can more than efficiently and reliably find content of interest.

With TAR 1.0 systems, yous are able to piece of work through a large volume of information more quickly and more consistently that would be case if one relied on human reviewers post-obit a traditional linear review process.

With TAR 2.0, you can greatly accelerate the review procedure without sacrificing, and indeed mayhap heighten, quality. That way, you can detect the content of consequence very quickly.

You likewise can use both processes, TAR one.0 and TAR ii.0, quality control, for example to evaluate your review team'southward work.

TAR Likewise Has Its Limits

TAR is valuable in many ways, merely it is not a tool for all seasons. Key considerations, when trying to determine whether TAR is correct for you, include:

• What you are trying to attain. If what TAR does fits with what you want to achieve, changes are good that TAR volition be able to help.
• What data you need to work with. TAR works with text. If the data yous take is non text or cannot readily exist converted to text, TAR probably won't be of much apply. If you accept audio files, TAR won't help. If, even so, you lot convert the contents of those audio files to text, the TAR can become a valuable tool to piece of work with that data.
• The richness of the content. TAR systems are designed to work with larger blocks of text such as documents and paragraphs. If your population of ESI consists primarily of short messages, say 10 words or less, TAR may not be an effective tool.
• Whether you take admission to someone who knows how to work with TAR. TAR is a tool, and as with any tool, is but as constructive as the people using it. If yous want to use TAR merely don't know where to kickoff, find someone knowledgeable who can help you. If you are at law firm, or legal department you lot might take a person or even entire section dedicated to litigation support or eDiscovery; go in that location. If yous don't have internal resource, look outside, for example to legal support providers (LSPs), with whom your organisation may already work.

TAR Volition Replace Me!

"TAR will supersede lawyers" is a variation of the oft-cited "John Henry versus the steam drill". As I discussed in Legal AI Software: Taking Document Review to the Next Level, TAR is not near human versus car.

Rather, TAR offers us the modern-day equivalent of The 6 Meg Dollar Homo, able to accomplish superhuman data analysis and review. If you prefer fact to fiction, AI software is the legal world'due south equivalent of the tethered exoskeleton arrangement being created past Hugh Herr's Biomechatronics group at the MIT Media Lab.

And so no, TAR is not most to replace u.s.a.. Instead, it opens upwardly new and powerful possibilities for making smarter, faster, and more informed decisions, letting y'all get to key content and develop essential insights quickly.

---

If your organization is interested in leveraging the power of legal AI software, contact Reveal to learn more. We'll be happy to evidence you how our authentic artificial intelligence takes review to the side by side level, with our AI-powered, end-to-stop certificate review platform.

loosegainglaing1952.blogspot.com

Source: https://resource.revealdata.com/en/blog/technology-assisted-review

Share this post