Machine Learning’s eDiscovery Roadmap.
Named-entity recognition ((NER) also known as entity extraction) seeks to locate and classify named entities in text into pre-defined categories such as the names of persons, organizations, locations, expressions of times, quantities, monetary values, percentages and more from text.
NER systems have been created that use linguistic grammar-based techniques as well as statistical models such as machine learning. Hand-crafted grammar-based systems traditionally have better precision, but at the cost of lower recall and months of work by experienced linguists. However, innovations with Machine Learning have brought these solutions to the mainstream and it’s finally affordable for everyone.
You log into your next document review and viewing a complete list of document categories, names mentioned, organizations and locations. Immediately view a facet-able timeline of content, a complete list of document types and custodians. Without performing a single string of query syntax, immediately understand the key players, timelines and understand how people communicate with each other. Millions of records can be indexed quickly and accurately at an extremely affordable cost.
This is the promise of Machine Learning powered Entity Extraction and today it’s available.
About Entity Extraction.
The Entity Extraction algorithm uses machine learning to reveal the structure and meaning of text. This allows us to quickly extract information about people, places, organizations, works of art and more. With entity extraction, reviewers better understand document content across vast collections of records of any kind in ways that just weren’t possible before without human-based objective coding.