Translation 24/7

Transforming Machine Translation Output into (Nearly) Flawless Content


Light and Full Post-Editing


When dealing with large volumes of documents, machine translation (MT) can offer a quick and cost-effective solution. However, without human involvement, important nuances or key information may be overlooked. To ensure the desired level of quality, two levels of post-editing are typically implemented: light and full.

Light post-editing

Light post-editing involves making minimal modifications to the raw MT output to ensure factual accuracy and grammatical correctness. Major and critical errors are addressed, while minor errors may be overlooked. The resulting text may sound robotic but remains understandable.

Light post-editing tasks include:

  • Correcting grammar and spelling mistakes only if they affect the meaning;
  • Rewriting confusing sentences (partially or completely).

The key phrases for light post-editing are ‘factual correctness’ and ‘good enough’.

Light Post-Editing

Full post-editing

Full post-editing is a more thorough and time-consuming process that aims to produce accurate translations with appropriate terminology, tone, style, and formatting. All errors are corrected, and the resulting text should read as if it were translated by a professional linguist.

Full post-editing tasks include:

  • Correcting ALL grammatical errors, typos, punctuation issues, and spelling mistakes;
  • Checking terminology against approved terminology resources;
  • Producing stylistically consistent, fluent content;
  • Applying correct formatting and tagging.

The expectation is high: fully post-edited content should be as fluent as human translation in all aspects. Therefore, the content must meet the quality criteria defined by the client for human translations.

Choosing the appropriate level of post-editing depends on the project’s quality needs and the client’s preferences. Quality can vary across projects, clients, and languages, and should be defined beforehand. It is also important to note that achieving human-level quality from MT output may require more effort than translating the content directly with a linguist. VILLAM's staff is happy to talk to you about finding the perfect solution.

The deciding factors to find the appropriate level of post-editing are:

  • Quality requirements: The level of post-editing required will depend on the quality requirements of the translation project. For instance, if the translation output is intended for internal use only, light post-editing may be sufficient. However, if the translation is intended for public consumption or legal purposes, full post-editing may be necessary.
  • Time constraints: Light post-editing is a quicker process than full post-editing. If there are tight deadlines, light post-editing may be the better option.
  • Cost considerations: Light post-editing is generally less expensive than full post-editing since it involves fewer modifications. If cost is a major factor, light post-editing may be the more economical choice.
  • Subject matter: Some subject matters may require a higher level of accuracy and precision, such as legal or medical documents. In such cases, full post-editing may be necessary.
  • Language complexity: Some languages may require more extensive post-editing due to their complexity or the differences between the source and target languages. For instance, machine translation between languages with vastly different structures or syntax may require more extensive post-editing.

Ultimately, the choice between light and full post-editing depends on the specific needs of the project, including the desired level of quality, time constraints, and budget. It’s important to discuss these factors with your language service provider to determine the best approach for your project.

If you are interested in using machine translation for your content, we are happy to discuss the levels of quality achievable through post-editing and determine the best-fit process for your needs.

Full Post-Editing