Technology-assisted review (TAR)
Also: predictive coding, continuous active learning, CAL
Software that helps rank documents for review. Some forms learn from a reviewer's choices. The process still needs testing and oversight.
The fuller definition
Technology-assisted review uses machine learning to rank or classify documents for relevance in large-scale review, learning from reviewer decisions. Continuous active learning is a common protocol.
The reference set has ten relevant events. Six are found, four are missed, and two additional returned items are unsupported. This example measures extraction, not every aspect of a legal work product.
A concrete example
Reviewers code a starting set. The system ranks the remaining collection so the documents most likely to be relevant are reviewed first.
The distinction that matters
TAR uses classification trained on your coding. It is not a generative assistant, and its results are measured with recall and precision on a sample.
Related terms
Classification
Sorting items into groups. For example, put each email in a group based on its topic.
Reliability & securityRecall
Of the things it should have found, how many it actually found.
Law & professional practiceeDiscovery
Finding and reviewing digital records for a legal case. It can include searching emails and deciding what must be produced.
Where it is taught
Design a review table before generating itSource and further reading
Sentence Transformers · Semantic searchThe definition and example are written for this library. The link gives background, official documentation or legal authority as labelled. Legal scope depends on the jurisdiction and current text; product features depend on release and settings.