CLICK HERE TO SEE BENCHMARK DATA FOR POSTEDITING PRACTICES GLOBALLY
This comprehensive report is the result of 5 years of TAUS monitoring of advances, best practices, issues and emerging trends in postediting. It contains insight for every reader from those with an expert knowledge of the area to new entrants to postediting. From organizations with complex global operations to the freelance translator.
Postediting is best understood as an integral part of the automated translation/localization process, rather than a separate stage of editing/revising/quality assurance. It requires linguistic more than subject area skills and is performed best by properly-trained alert translators, familiar with machine output, working to clear instructions in a standard translation environment.
Publication quality postediting should be able to output at least 5,000 translated words a day, whereas lighter editing for gisting (assimilation) can double this rate. Since the overall aim of any translation automation solution is to accelerate throughput at consistent quality levels (and where possible reduce costs), ongoing efforts to optimize postediting are focused on improving raw translation quality to maximally reduce the postediting workloads.
This report focuses on three currently evolving aspects of postediting practice:
- the impact of statistical machine translation on the postediting cycle;
- problems in specifying target quality for postedited texts; and,
- efforts to improve guidelines for human post-editing practices.
Now that end users can in certain contexts choose between statistical and rule-based MT engines, the postediting stage may become a selection criterion. Before undertaking full deployment, LSPs and end users will usually need to run quantifiable evaluation pilots to inventory post-editing tasks, identify recurrent modifications for automatic solutions, and base expectations about quality and pricing on objective data.
Based on feedback from the LSP workforce, we also examine difficulties encountered by posteditors, and pinpoint strategies for overcoming them. Generally speaking, postediting is still a nascent profession and considerable experimentation with MT systems, human resource profiles, and technological fixes will be needed to help LSPs add value to their postediting services.
Contents
People and organizations in the report
Charts
| Non Members | Members |
| Purchase the full report | Download the full report |
 |
 |
| (PDF - € 265) | (PDF - 528Kb) |
