Category Archives: TAR 2.0

Is Mandatory TAR on the Horizon?

Is  mandatory technology-assisted review on the horizon? This was question that Tom Gricks and John Pappas posed in a recent Bloomberg article.

Cost continues to be the primary issue lying at the heart of e-discovery disputes, particularly with the amendments to the Federal Rules of Civil Procedure (FRCP), specifically Rule 26, mandating that the scope of discovery in litigation be proportional to the value and needs of the case. Judges are increasingly being called upon to resolve these disputes and explicitly consider the fact that the cost and efficiency of different review techniques and technologies can still vary widely. Continue reading

TAR 2.0: Using Contextual Diversity to Find Out What You Don’t Know (and a Bit About Zipf’s Law)

In the early technology assisted review (TAR 1.0) era, many thought training with randomly selected documents was important to the success of a TAR review. The fear was that attorneys would bias the TAR algorithm if they selected documents for initial training. When challenged, most relied on the old shibboleth: You don’t know what you don’t know.

Frankly the “don’t know” point made sense at a time when legal professionals were just realizing that their carefully crafted keyword searches were failing because their targets used different terms. If lawyer keywords couldn’t be trusted, why trust lawyer-selected training seeds? And, random selection was the cornerstone of the TAR 1.0 protocol called simple passive learning. The computer passively (randomly) selected all the training documents. Continue reading

The New AI Executive: 6 Must-Reads for Legal

The recent Executive Order on artificial intelligence (AI), though directed at federal agencies to prioritize AI investment in research and development, is likely to continue to spur the conversation on use of AI and machine learning in the legal realm.

This is particularly so in e-discovery, where technology-assisted review (TAR), a form of AI, is seeing greater acceptance and refinement in the legal space—that is, helping corporate legal departments take control of review costs and enabling law firms to provide superior and differentiated services to their clients.

But with a deeper understanding of the technology, distinction between TAR 1.0 and TAR 2.0 systems like Catalyst’s Insight Predict (based on the continuous active learning, or CAL, protocol), and advancements to take maximum advantage of TAR techniques on more review tasks, AI can be even more useful and effective in the legal world.    Continue reading

And the 2018 Award Goes to… TAR 2.0

By on . Posted in TAR 2.0

As an annual tradition, we compile a list of the most widely read Catalyst blog posts of the previous year to see what topics most interest our readers. Here are our top five most popular blog posts of 2018.

1. 57 Ways to Leave Your (Linear) Lover

What’s more fun than running 57 simulations for a client investigation? Seeing the results.

We structured a simulated review on Insight Predict, our TAR 2.0 platform, to be as realistic as possible, looking at the client’s investigation from every conceivable angle. The results were outstanding, so we ran it again, using a different starting seed. We did 57 different simulations starting with relevant seeds (singularly with each relevant document), a non-relevant seed and a synthetic seed. Regardless of the starting point, Predict was able to locate 100% of the relevant documents after reviewing only a fraction of the collection.

Continue reading

High-Efficiency Review Enables Client to Meet Short Deadlines; Significantly Reduces Costs

Catalyst Managed Review + TAR 2.0 Finds 94% of the Relevant Documents

Our client, a global corporation, was facing an investigation by a government agency into alleged price fixing. The regulators believed they would find the evidence in the documents and issued a broad request—with just four months to get the job done.

This wasn’t a case of finding a needle in a haystack. Rather, a wide range of documents were responsive. A sample of the initial collection suggested that as many as 45% of the documents would be responsive. One option was to produce everything but the client had a significant amount of confidential and proprietary information that it did not want to be inadvertently exposed. Thus, they needed to produce responsive documents, but only responsive documents. Continue reading

Breaking Up the Family: Reviewing on a Document Level Is More Efficient

Lawyers have been reviewing document families as a collective unit since well before the advent of technology-assisted review (TAR).

They typically look at every document in the family to decide whether the family as a whole (or any part of it) is responsive and needs to be produced, or withheld in its entirety as privileged. Most lawyers believe that is the most efficient way to conduct a review. Continue reading

Can You Do Good TAR with a Bad Algorithm?

Should proportionality arguments allow producing parties to get away with poor productions— simply because they wasted a lot of effort due to an extremely bad algorithm? That was a question that Dr. Bill Dimm, founder and CEO of Hot Neuron (the maker of Clustify software), posed in a recent blog post, TAR, Proportionality, and Bad Algorithms (1-NN) and it was the subject of our TAR Talk podcast.

This question is critical to e-discovery, and especially relevant to technology-assisted review (TAR). Listen to our short podcast led by Bill, with participants Mary Mack from ACEDS, and Catalyst’s John Tredennick and Tom Gricks, in a discussion on whether one can do “good” TAR with a bad algorithm. Continue reading

Are People the Weakest Link in Technology Assisted Review? Not Really.

In mid-October, our friend Michael Quartararo wrote a post for Above the Law asking whether people were the weakest link in technology-assisted review (TAR). Michael offered some thoughts around whether this may be the case, but he didn’t really answer the question. So, we have to ask:

Why aren’t more people using TAR?

One answer is that there is still a lot of confusion about different types of TAR and how they work. Unfortunately, it appears that Michael’s post may have added to the confusion because he did not differentiate between legacy TAR 1.0 and TAR 2.0. Our first thought was to let the article pass without rejoinder or correction. To our surprise, however, it has been cited and reposted as authoritative by several others. To that end, we want to help clarify a number of Michael’s points. We will quote from his post. Continue reading

Using TAR for Asian Language Discovery

In the early days, many questioned whether technology assisted review (TAR) would work for non-English documents. There were a number of reasons for this but one fear was that TAR only “understood” the English language.

Ironically, that was true in a way for the early days of e-discovery. At the time, most litigation support systems were built for ASCII text. The indexing and search software didn’t understand Asian character combinations and thus couldn’t recognize which characters should be grouped together in order to index them properly. In English (and most other Western languages) we have spaces between words, but there are no such obvious markers in many Asian languages to denote which characters go together to form useful units of meaning (equivalent to English words). Continue reading

Was It a Document Dump or a Deficient TAR Process?

TAR TalkThat’s the topic of our recent TAR Talk podcast.* We talked about the recent decision by the U.S. District Court for the District of Columbia In Re Domestic Airline Travel Antitrust Litigation, 2018 WL 4441507 (D.D.C. Sept. 13, 2018), an antitrust class action lawsuit against the four largest commercial airlines in the United States—American Airlines, Delta Air Lines, Southwest Airlines, and United Airlines.

The declarations around this decision prompted much discussion in the e-discovery world, particularly for those using technology-assisted review (TAR) in the review process. The argument was based on United’s core document production. The plaintiffs called it a deficient TAR process and complained that they were forced to review mountains of non-relevant documents (aka, a document dump). Continue reading