Published: June 2025
Where Published: Submitted on 27 May 2024 (v1), last revised 5 Aug 2024 (this version, v5) — https://arxiv.org/
Summary
The year 2024 marks the 10th anniversary of the Multidimensional Quality Metrics (MQM) framework for analytic translation quality evaluation. The MQM error typology has been widely used by practitioners in the translation and localization industry and has served as the basis for many derivative projects. The annual Conference on Machine Translation (WMT) shared tasks on both human and automatic translation quality evaluations used the MQM error typology.
The metric stands on two pillars: error typology and the scoring model. The scoring model calculates the quality score from annotation data, detailing how to convert error type and severity counts into numeric scores to determine if the content meets specifications. Previously, only the raw scoring model had been published. This April, the MQM Council published the Linear Calibrated Scoring Model, officially presented herein, along with the Non-Linear Scoring Model, which had not been published before.
This paper details the latest MQM developments and presents a universal approach to translation quality measurement across three sample size ranges. It also explains why Statistical Quality Control should be used for very small sample sizes, starting from a single sentence.
Key Takeaways
- Presents and explains a methodology for translation quality measurement that adapts across three sample size ranges, from very small samples (even a single sentence) to large datasets. Advocates using statistical quality control for evaluating very small volumes, underscoring the importance of robust approaches even in minimal data scenarios.
- Introduces the Linear Calibrated Scoring Model (officially published by the MQM Council in April) and presents a Non-Linear Scoring Model (unpublished before).
- MQM error typology is widely adopted for both human and automatic translation quality evaluation — used in high-profile venues like the annual WMT (Conference on Machine Translation) shared tasks.