AI & Machine Learning in Document Review

Sooner or later, most e-discovery professionals have experienced the pressure of a slow-moving document review. Pressure to reduce time spent with review and cost control is a major reason that eDiscovery is prime real estate for the current blooming use of artificial intelligence (AI) in law.

Machine learning is an area of AI that enables computers to self-learn, without explicit programming. In e-discovery, machine-learning technologies such as technology-assisted review (TAR) are helping legal teams dramatically speed document review and thereby reduce its cost. TAR learns which documents are most likely relevant and feeds those first to reviewers, reducing the need to review from 50 to 90 percent of a total review population.

There are various ways that AI is integrating within current law and eDiscovery practices but here are a few examples to expect in 2021. As the legal landscape evolves it is important to stay current with new technology and practices in order to stay ahead of the curve, reduce cost, and minimize risk.

  • Deep Learning Based AI- In eDiscovery, machine learning for document classification goes by many names, but the two most common are technology assisted review (TAR) and predictive coding, which are used more or less interchangeably. Regardless of what they are called, they generally fall into one of two categories:
    • Simple Passive Learning (or TAR 1.0): A subject matter expert classifies some documents to be used for training, which the system then uses to test the reliability of the predictions as more documents are classified. Once the performance is acceptable, the prediction model is rolled out to all remaining documents.
    • Continuous Active Learning (or TAR 2.0): All review decisions automatically train the system, and the system continually updates the predictions as new human classifications are made.

  • AI in Document Review – Rather than processing exhaustive sets of rules, AI solutions recognize key terms while also understanding the context such as the meaning of words, sentence structures, and word choice patterns. As reviewers perform their jobs, the AI algorithms learn and refine their understanding of which documents are relevant and apply labels to unreviewed documents with a corresponding confidence score, helping reviewers view the most highly likely relevant documents sooner—saving considerable time and expense. This approach requires no seed sets, no additional training, and no changes to current review processes, as the algorithms work in the background while reviewers complete their tasks.
  • AI Driven Early Case Assessment – AI in ECA identifies responsive data prior to collection through examining the relationship between custodians and the content, allowing you to explore communication patterns and concept clusters to get to the facts of each matter  more effectively.

Leave a Comment

You must be logged in to post a comment.