Automatic Correction of Human Translations
This addresses the overlooked issue of correcting human translation errors, which is incremental as it adapts existing post-editing methods to a new task.
The paper tackles the problem of automatically correcting human-generated translations by introducing translation error correction (TEC), showing that pre-training on synthetic errors improves TEC F-score by up to 5.1 points and that a TEC system assists professional editors in producing higher quality revisions.
We introduce translation error correction (TEC), the task of automatically correcting human-generated translations. Imperfections in machine translations (MT) have long motivated systems for improving translations post-hoc with automatic post-editing. In contrast, little attention has been devoted to the problem of automatically correcting human translations, despite the intuition that humans make distinct errors that machines would be well-suited to assist with, from typos to inconsistencies in translation conventions. To investigate this, we build and release the Aced corpus with three TEC datasets. We show that human errors in TEC exhibit a more diverse range of errors and far fewer translation fluency errors than the MT errors in automatic post-editing datasets, suggesting the need for dedicated TEC models that are specialized to correct human errors. We show that pre-training instead on synthetic errors based on human errors improves TEC F-score by as much as 5.1 points. We conducted a human-in-the-loop user study with nine professional translation editors and found that the assistance of our TEC system led them to produce significantly higher quality revised translations.