Skip to main content

XTM Cloud 25.3

Matches docked panel

XTM Workbench displays matches in the docked panel. They are ordered by the type of match and then by the date created or changed. The order is as follows:

  1. In-context Exact match (ICE).

  2. Leveraged match 100%.

  3. Repetitions.

  4. TM Fuzzy matches.

  5. Internal Fuzzy matches (in score order and then in date order).

  6. MT matches.

Intelligent Score results in XTM Workbench

Note

This is a Beta feature.

If your XTM Cloud Administrator has activated the Intelligent Score feature for your instance, you will see the Intelligent Score results in the Metadata column, in the Matches docked panel.

The Intelligent Score feature automatically evaluates the quality and accuracy of translations generated by an LLM (Large Language Model). For every eligible segment, the feature compares translations generated by three different LLMs and evaluates their similarity. The lower the similarity of these three translations, the lower the quality evaluation score (percentage).

Table 100. Intelligent Score values in the Metadata column

IS COLUMN VALUE

DESCRIPTION

Percentage on a red background and an error icon warning-exclamation-red.png

The LLM-translated target segment has been evaluated as a Not acceptable (poor) quality segment. It means this segment needs corrections or post-editing by a Linguist. Hover over the result in the IS column to see the improvement suggestions.

Percentage on a yellow background and a warning icon QA_warning_gray.svg

The LLM-translated target segment has been evaluated as an Acceptable (medium) quality segment. It means this segment meets basic standards, but a Linguist might need to make minor improvements to it. Hover over the result in the IS column to see the improvement suggestions.

Percentage on a green background and a checkmark icon black_circle_checkmark.svg

The LLM-translated target segment has been evaluated as a Good (high) quality segment. It means this segment does not need any corrections or post-editing. Still, you can hover over the result in the IS column to ensure there are no improvement suggestions.

N/A

The LLM-translated target segment has been manually edited by a user. In this case, neither the Intelligent Score result nor suggestions are displayed.


In this section:
TM Expert