Exterro Smart Labeling Release Brings the Most Advanced Use of Artificial Intelligence (AI) to Document Review
New deep learning–based capability is the first instantiation of Exterro’s vision to infuse AI throughout the entire e-discovery process.
PORTLAND, Ore., May 22, 2018 – Exterro® Inc., the preferred provider of software designed for in-house legal and IT teams at Global 2000 and AmLaw 200 organizations, announced the launch of Exterro Smart Labeling, an advanced use of Artificial Intelligence (AI) within the Exterro Review Platform.
Exterro Smart Labeling leverages the latest deep learning technology to help guide reviewers by continuously analyzing and understanding the context of their labeling decisions. The system then suggests or queues the most relevant unreviewed documents, significantly reducing review time and associated costs.
“Exterro Smart Labeling is built upon the latest innovations in deep learning, natural language processing, compute-intensive hardware processing, and related architectural approaches, delivering far superior results and experiences compared to previous machine learning or continuous active learning approaches,” said AJ Samuel, Chief Product Officer at Exterro.
Exterro’s Smart Labeling algorithms interpret language in ways that mimic how the human brain functions. Instead of processing large rule sets, the technology recognizes key terms and understands context, including:
- The meaning of words
- Sentence structure
- Word choice patterns
As reviewers perform their work, the Smart Labeling algorithms continuously learn and refine their understanding of document relevance. The system can then automatically apply labels to unreviewed documents along with a confidence score, allowing reviewers to prioritize the documents most likely to be relevant.
This approach enables teams to review critical documents earlier in the process, saving significant time and cost.
The solution requires:
- No seed sets
- No additional training
- No changes to existing review workflows
The algorithms operate in the background while reviewers complete their normal tasks.
“At NightOwl Discovery, we are always looking for advanced technologies that help our clients meet discovery, compliance, investigations, and data analytics objectives,” said Kelly Atherton, Director of Analytics and Managed Review at NightOwl Discovery.
“The use of deep learning AI technology like Exterro’s Smart Labeling is a powerful way for us to optimize the document review process for our clients.”
Exterro Smart Labeling represents the first step in Exterro’s broader artificial intelligence strategy to incorporate AI across the entire e-discovery lifecycle.
In the near future, Exterro plans to introduce additional AI capabilities designed to improve efficiency in the identification, preservation, and collection stages of the Electronic Discovery Reference Model (EDRM).
