Translation industry think-tank the Translation Automation Users Society (TAUS) and Ireland’s world-leading Centre for Next Generation Localisation (CNGL) have published a set of guidelines that will serve as guidance for customers and service providers in the translation industry who are exploring the new territory of machine translation post-editing.

Post-editing is the correction of machine-generated translation output to ensure it meets a level of quality negotiated in advance between client and post-editor.
The increased use of machine translation by clients and language service providers has generated a more substantial need for post-editors; however, language specialists have been reluctant to offer this sought-after service due to an absence of clear guidelines and acceptance criteria.

Guidelines for achieving “good enough quality”

“Good enough” is defined as comprehensible (i.e. the main content of the message be understood), accurate (i.e. it communicates the same meaning as the source text), but as not being stylistically compelling. The text may sound like it was generated by a computer, syntax might be somewhat unusual, grammar may not be perfect but the message is accurate.

• Aim for semantically correct translation.
• Ensure that no information has been accidentally added or omitted.
• Edit any offensive, inappropriate or culturally unacceptable content.
• Use as much of the raw MT output as possible.
• Basic rules regarding spelling apply.
• No need to implement corrections that are of a stylistic nature only.
• No need to restructure sentences solely to improve the natural flow of the text.

Guidelines for achieving quality similar or equal to human translation

This level of quality is generally defined as being comprehensible (i.e. an end user perfectly understands the content of the message), accurate (i.e. it communicates the same meaning as the source text) and stylistically fine, although the style may not be as good as that achieved by a native-speaker human translator. Syntax is normal, and grammar and punctuation are correct.

• Aim for grammatically, syntactically and semantically correct translation.
• Ensure that key terminology is correctly translated and that untranslated terms belong to the client’s list of “Do Not Translate” terms”.
• Ensure that no information has been accidentally added or omitted.
• Edit any offensive, inappropriate or culturally unacceptable content.
• Use as much of the raw MT output as possible.
• Basic rules regarding spelling, punctuation and hyphenation apply.
• Ensure that formatting is correct. Read more.

See: Centre for Next Generation Localization