Reviewing dupes for Continuous Active Learning in Relativity

When conducting active learning (CAL) in Relativity, keep in mind that you have a choice between whether or not the reviewers will be given documents which are textually similar to those which a coder has already determined to be responsive or non-responsive.

The Suppress Duplicate Documents setting should be set to Yes you are performing 'coverage review' in order to train the system as quickly as possible. In this model, the documents which the system is most uncertain about will be added to the review queue first - those with a rank around 50 on the scale from 0 to 100.

Prioritized review will prompt reviewers to focus on the highest ranking documents. When this type of review is performed the reviewers will code the highest ranking documents first.

Once a project has been started, the suppress duplicates setting cannot be changed.

The documents which are suppressed for a classification will be tagged in the field tree, so they can be reviewed earlier.

RelativityOne's Redact

Keep in mind the following about RelativityOne's new redact function.

• Redact will store a record of the original version of a document that is redacted for a production set.

• After a cell is redacted, most of the formatting in the cell will be retained. The cell border and color fill will not be lost. However only the format settings for the first word in the cell will be saved. Other variations to the font, font size, and text color for subsequent words will be lost.

• While Redact will facilitate the redaction of Excel files, it is not possible to use it to redact .csv files.

• Users with access to Redact will be able to use these mass operations:

  1. Convert spreadsheet markups - this changes all redactions to highlights, or vice versa.

  2. Revert redactions for native files

  3. Remove hidden content in Excel files.

Relativity filters

Be sure not to miss the following facts about filters in Relativity:

• Any term entered directly in the search box for a filter will be treated like a wildcard.

. . . if you enter an asterisk in the filter, it will be treated as a searchable character, and you may not get results for the stem preceding the asterisk.

You can use an underscore _ to search for a missing character:

Don't enter parentheses in a search for a phrase, just enter the phrase itself. Using an = sign before a term will run an exact search.