Post-editing

EQHO’s hybrid automated translation and human post-editing model enables companies to scale their translations at a fraction

TRANSLATE HIGH VOLUME NON-CRITICAL
CONTENT TRANSLATE MORE, FOR LESS

Arguably one of the most talked about areas of the language business, Automated Translation (AT) cannot be ignored.

With major advances in machine translation technology and advanced content leveraging, and the ever increasing demand for global content and fully native brand experiences, the AT and human post-editing translation model is an obvious ‘go-to’ solution for corporations looking to disseminate maximum amounts of content, quickly and efficiently. Although AT isn’t suitable for every application; where it is, it can make it feasible to translate high-volumes of content at reduced costs and in shorter timeframes.

Light post-editing

Light post-editing requires minimal intervention by the post-editor, and is primarily intended to help the end-user understand the meaning of the content. Typical purposes are for company internal usage, often when the text is needed urgently, where the project has a short timeframe, or as an intermediate step in the full AT process.

Full post-editing

Full post-editing requires a higher level of interaction and an elevated level of quality; the expectation is that the output will be a translation that is not only accurate but also stylistically appropriate. Typical uses for full post-editing AT include external company use, similar to if not the same as expectations of translations produced by human linguists.

Some things to consider:

LANGUAGE PAIRS

Some languages and combinations lend themselves better to AT and therefore yield higher productivity gains (e.g. Spanish, French, Italian), while other languages are still less suitable to the use of AT (e.g. Japanese)

SOURCE LANGUAGE QUALITY

The ‘garbage-in garbage-out’ theory. Better source language control and use of authoring tools will inevitably increase the match yield achieved from AT. This includes use of grammar and style rules and terminology.

LEGACY CONTENT/ DOMAIN-SPECIFIC CORPUS

Particularly in the case of Statistical Automated Translation methods, the more significant the size and the quality of legacy content that can be used to train the AT engine, the higher the yield of match that can be achieved.

CUSTOMER-SPECIFIC/ DOMAIN DICTIONARIES

In the same vein as legacy content or corpus availability, customer-specific or domain dictionaries can significantly improve the quality of AT output, and associated AT cost benefits.

contact

Are your translation solutions scalable?

As experts in Asian localization and translation services, with more 20 years of experience, EQHO is the ideal choice. To find out more about how localization can benefit your business, or to get started, contact us today.

This website uses cookies to improve your experience. By continuing to use our site you agree to our Privacy Policy. ACCEPT