Quality Metrics

Multidimensional Quality Metrics (MQM)

Multidimensional Quality Metrics (MQM) is a framework for describing and defining custom translation quality metrics. It provides a flexible vocabulary of quality issue types, a mechanism for applying them to generate quality scores, and mappings to other metrics. It does not impose a single metric for all uses, but rather provides a comprehensive catalog of quality issue types, with standardized names and definitions, that can be used to describe particular metrics for specific tasks.

The MQM definition is online here. Interested parties are encouraged to review the specification and provide feedback. Additional information about earlier versions of MQM is also available from the website of the QTLaunchPad project here.

Relationship to TAUS Dynamic Quality Framework (DQF)

The TAUS Dynamic Quality Framework provides a set of industry-developed tools for evaluating translation quality. One of the methods, the DQF Error Typology, is a subset of MQM that is tuned for the needs of assessing quality in typical localization projects using an “error count” method and is recommended for use in this environment. DQF provides additional tools and methods as well that are useful for evaluating quality using additional methods not directly addressed by MQM.

Feedback

The primary mechanism for providing feedback on MQM is via the project’s GitHub page. Comments should be submitted as issues there so that they can be tracked and publicly responded to. Anyone who does not wish to publicly post comments can also send them to Arle Lommel and Attila Görög. Anonymous comments will be posted to the GitHub tracker by the project team.