Human Post-Editing of Machine TranslationsAlthough machine translation technology has made impressive advances in recent years, it cannot yet replace the discerning judgment of a skilled human translator. At Trusted Translations, we recognize that the two work best in tandem, with a human translator post-editing translations done by machine.
Have machine translations reached full parity with humans? Not quite—which makes a human touch essential. The accuracy and effectiveness of machine translations will depend on numerous factors, such as language combination, content domain, complexity and technical level, whether the content is prosaic or creative, how well-written the source content is, input format, and more.
Due to these infinite variations, machine translations are not able to detect every linguistic nuance and produce a correct translation in every instance. In most cases, to guarantee a highly reliable translation output when utilizing machine translation, human post-editing is indispensable. Moreover, if you are using a Custom Neural Machine Translation Engine (CMTE), feedback from a human linguist is necessary for retraining purposes to improve performance.
At Trusted Translations, we have expert linguists trained specifically to post-edit machine-generated translations. Our skilled post-editors rely on their experience with machine or automated translation output not only to provide corrections, but also to improve future output.
With the right technology tools in place, the post-editing process will improve the output quality of a current translation project, allow you to store that quality data in your translation memory (TM), and also improve the efficiency and accuracy of the machine translation engine for future projects.
Translating and Post-Editing Processes
The processes of translating and post-editing machine-generated content are quite different; each one calls for distinct skills and training. Not all translators are comfortable doing post-editing; even if they sign on for post-editing, they often require training.
- Quite recently, academia has started developing curricula to address the growing demand for human post-editors. This training begins with the mental process used when reviewing bilingual content. When translating content from scratch, faced with a “target” (the would-be translation) that is a blank canvas, translators normally:
- Read the source content carefully.
- Formulate the translation internally (i.e., in their brain).
- And finally, type their version in the target language (translation) in a software program or interface.
- Depending on the content and project, the translator may edit the text immediately, conduct additional research, or return to it later when the entire text has been translated.
- In post-editing machine translated content, however, the process is very different, and it is generally performed with the use of a computer-assisted translation tool (CATT):
- First, the post-editor (linguist) reads a sentence, or segment, of the MT output (that is, the process begins at the target).
- The MT output is compared to the source text.
- The post-editor makes an in-the-moment judgment of the MT output’s quality, based on linguistic knowledge and explicit instructions.
- If the MT output is acceptable, they continue working to improve the text.
- If the MT output is of poor quality, they delete whatever the MT is offering and re-translate it from scratch (as in the translation process listed above).
As part of a machine-translation post-editing process, the project will often include a translation memory (TM) that contains translation segments from previous translation jobs of similar/related material, usually from clients or other similar projects. These previously translated segments contained in the TM, may be either a fuzzy (an approximation) or a full match of the current source segment. Taking a look at what the TM offers, the post-editor can either use these previous translation segments in their entirety or make the necessary adjustments.
Human Post-Editing and Human Translation
There is a significant difference in the skills and approach involved when reviewing human translations versus machine-generated translations. In general, the types of errors found in human translations differ greatly from those found in machine-translated text. For example, machine translations have a tendency to be more accurate when transposing numerical values. Machine engines are also less prone to leaving content behind (e.g., omitting a clause within a long legal paragraph). However, machine translations also tend to produce more awkward-sounding phrases. Some MT engines may also perform very poorly with terminology.
Human translations, on the other hand, tend to be better at creating a natural-sounding output, with fewer errors in context and meaning, while being more prone to errors when translating numerical values. A linguist is also more prone to making omissions. Some may even be prone to adding content when purposely trying to disambiguate. But that certainly strays from the source. At Trusted Translations, we train our machine translation post-editors to recognize these differences and to utilize our proprietary tools to improve the output. Furthermore, our tools help the editor re-translate awkward-sounding phrases in a manner that “trains” the machine translation engine to improve on future output.
Light and Full Post-Editing
At Trusted Translations we adhere to the principle that there is no one-size-fits-all solution, and that we must adapt every solution to our clients’ needs.
If quality is the driver, we evaluate not only the prospect of the engine’s performance, but also the level of post-editing needed according to the usability of the output. In this case, a full (ready-to-publish) post-editing is requested as the output for this task. That is to say, if the bilingual content were to go through an additional review step (editing, for instance), the editor should not detect any differences between an MT post-edited segment and a 100% HT (human-translated) segment.
If cost is the driver, or if time is of the essence—and the quality of the MT output is decent enough—we may recommend only light post-editing to make the text flow better, correct major grammatical errors with the help of a spell-checker, and even improve terminology usage.
Post-Editing and Pre-Editing
Post-editing should not be confused with pre-editing. Pre-editing refers to the preparation involved prior to running a particular text through an automatic translation tool. It involves reviewing the content for basic errors, tagging certain content to be translated a certain way (or to not be translated at all), and optimizing the formatting. This preparation prior to utilizing the translation tool can greatly improve output quality and is considered a vital step in most machine or automated translation projects.
Incorporating an efficient pre-editing process can vastly improve the output, making it easier for the post-editors to do their job and produce a quality translation. As machine translation technology continues to improve, it will be vital to have the necessary human skills in both the pre-editing and post-editing processes in order to produce high-quality translations.