Semantic search

Semantic search finds passages by meaning rather than by exact words, so a search for termination on insolvency can find a clause that refers to administration or winding up instead.

Last updated

What it means for a UK law firm

Semantic search helps with legal documents because drafting styles vary between firms and counterparties. A keyword search misses clauses that express the same idea in different words; semantic search ranks passages by how close their meaning is to the query.

Semantic search can also return passages that look related but are not on point, so its results are a starting point for review rather than a complete list. Where completeness matters, such as in disclosure, firms should combine semantic search with other methods and record what was searched.

Example

Illustrative scenario

A solicitor searches the firm's precedent library for a limit on liability for data loss. Semantic search returns a precedent clause headed “Exclusions” that caps recovery for corruption or destruction of information, wording that a keyword search for “data loss” would not have found.

How Chancery handles it

Chancery lets you search clauses in plain English while drafting, and ask questions in plain English across a matter, all of your matters or your precedent library; see Drafting and Matters.

Related terms

This glossary entry is general information, not legal advice. See the full legal AI glossary for other terms.

Give your firm the same advantage as the top 20, at a price that makes sense for yours.