MTPE — or machine translation post-editing — has quickly gained prominence as a way to achieve high-quality translations at a lower cost than the traditional human-only translation workflow.
Artificial intelligence (AI) has supercharged traditional MT and MTPE workflows and provided an even better way to get high-quality translations for less. Smartling customers can leverage Smartling’s AI-powered MT workflow to do most of the heavy lifting. And that means they can reserve the use of human post-editing by expert linguists for their highest-priority translations.
What is Machine Translation Post-Editing (MTPE)?
Machine Translation Post-Editing (MTPE) combines the accuracy of human translators with the speed of machine translation. At Smartling, this means a translation process where professional editors review the machine-translated output and translation memory matches to ensure high-quality work.
The entire translation process looks like this:
Machine translation engines translate the source text into the target language.
Smartling’s software applies preferred terminology to language resources and edits for spelling or grammatical errors.
Professional translators then review the translated text, performing light post – editing as needed to ensure consistency in voice, fluency, and accuracy .
Machine translation may not be a replacement for humans yet, but it can be a significant first step for companies starting their localization efforts or expanding into new markets. Suppose you’re looking to quickly deliver accurate translations for software or web pages , or you only need to support one or two languages. In that case, machine translation can be a great option, especially if you add post-editing services from a professional translator to the mix for an extra layer of quality assurance of the translated text.
Is Machine Translation Post-Editing Right for Me?
When considering which translation services to use, it’s important to ask yourself: What level of quality is acceptable for the type of content I’m translating? At Smartling, we’ve found that there’s an ideal solution for every translation use case, but it may look different for every company.
Let’s start by comparing MTPE to other popular translation options.
MT vs. MTPE
Neural machine translation offers one of the fastest and most cost-effective ways to translate text between different languages. Most machine translation tools automatically deliver results within minutes or seconds, provide consistent results, and support a wide range of languages. Finally, as MT has evolved and neural machine translation (NMT) engines have matured, the raw output of MT has become more accurate.
Machine translation engines essentially produce a good basic translation, so MT is a great choice when a basic translation is all that’s needed. For example, we often recommend dedicated MT workflows for content that has a short argentina whatsapp number data 5 million shelf life, is time-sensitive , or doesn’t require a strong personality in the translated text. Support tickets, technical manuals, and customer reviews can all fall into this category. It’s also a great tool for secondary translation efforts, such as retranslation (editing a word or two instead of sending an entire paragraph) or pretranslation (getting a feel for how expanding the text will affect your user experience).
Traditional MTPE complements the advantages of MT by adding quality control by a professional translator. This allows you to enjoy some time and cost savings while also increasing the level of output quality.
MTPE typically takes two forms, depending on your needs: full post-editing (FPE) or light post-editing (LPE). Light post-editing scans your document for glaring issues, such as major grammatical errors, spelling mistakes, or misspelled words. This provides a faster turnaround, but lacks the depth of FPE, a full, detailed human edit for style, brand voice, and consistency. Your choice of FPE or LPE depends on the quality of your initial MT output and your use case.
MTPE versus human translation
Neural machine translation engines can provide relatively accurate and consistent basic translations instantly and for much less money. And professional translators can offer cultural expertise and knowledge that helps improve those translations. So why not use MTPE for everything?
While it’s true that post-editing can increase the quality of your machine-translated output, it’s not always a substitute for a human translation workflow. Certain types of content, such as high-profile marketing content and translations that require a lot of creativity and cultural sensitivity, require a human touch.
In essence, a professional linguist creates a how to use short-form video in digital marketing final product that sounds like it was written in your target language, with your specific local audience in mind. This isn’t something that software can capture. Furthermore, an MT-generated translation doesn’t always provide a great starting point for many of the types of content for which you’d want a human-only workflow.
The more complex, detailed, or confidential your content is, the more likely you are to need professional translation services. That’s why Smartling works with a network of professional translators around the world who specialize in not only ensuring that your translations are accurate, but also that they align with your messages and sound as if they were originally written in the target language.
AI-powered translation workflows
Recent advances in AI have introduced new ways of working. Those who use AI in translation are finding that they have room in their budgets to translate more content than ever before. They’re also doing it faster and without sacrificing quality.
Smartling’s AI translation workflow japan data uses AI to enhance the traditional machine translation post-editing process. First, we use AI fuzzy match repair to apply your translation memory and repair highly fuzzy matches. Next, your strings are sent to multiple MT engines and AI is used to select the best raw translation. Finally, an AI post-editing step applies preferred terminology from language resources and corrects grammar, syntax, style, and formality.
Translations are delivered to you instantly. Plus, they’re the same quality you’d get with traditional MTPE — at half the cost.
Smartling customers have found that the AI translation process delivers sufficient quality for many use cases where they would have previously used MTPE. This includes user guides and contracts, white papers, case studies, and knowledge base and help center articles.
Better yet, they’ve found that this workflow provides excellent basic translation for high-profile content, such as marketing website and product packaging. Where they once used a human-only workflow, they now typically hire professional translators and linguists only as light post-editors—and achieve the same level of quality. Human-only translation, then, could be reserved for projects that require a creative and culturally attuned touch.
5 Best Practices for Machine Translation Post-Editing
Taking a hybrid approach to your translation needs, combining machine translation with a human post-editing step, requires you to follow some best practices to ensure good results. If you choose to put some of your content into a traditional MTPE, here are some things to keep in mind.
1. Make sure the source text is as clean as possible
It’s easy to complain about MT’s accuracy, but often the culprit isn’t the software; it’s the original text! Awkward sentences, grammatical errors, punctuation mistakes, and inconsistent terminology in the source text can all be carried over to the machine-translated output.
A lack of consistency can create confusion for your human editors and therefore result in a poor translation. Therefore, it is important to have someone review your original text before translation and make sure it is as accurate and error-free as possible.
This is especially important for more specialized industries like finance or medicine, or for more elaborate types of content like transcription and subtitling.
2. Choose the right TMS for your needs
There are many neural machine translation engines out there, including Google Translate, DeepL, and Microsoft Translator. But what you want is a translation management software (TMS) like Smartling that can manage the entire localization process in one interface, whether you’re requesting machine translation or MTPE or need a more customized approach through other translation services.
Smartling Translation Management System is a repository for your content and a powerful administrative suite to control everything related to localization:
Track real-time translation progress for websites, mobile apps, emails, and more in one place.
Configure Smartling to automatically send content for translation based on a set of pre-determined conditions, such as budget, workflow requirements, and schedule.
Set up dozens of quality check options to ensure consistent translations across all your content, without having to check everything yourself.
The right TMS will also include CAT tools to help linguists offer post-editing services such as translation memory, glossary, and style guides to their entire translation team. These tools have been proven to improve the accuracy of final translations.
3. Establish clear editorial guidelines
Whenever you have a team of translators editing your content, you need to have a place to find all the information they need. Document everything in your language asset pack. This should include your preferred terminology and brand style (do you use the Oxford comma?) to paragraph length, preferred tone, brand voice, and formality.
That’s because what might be appropriate in your source language won’t work in your target language. Think about brands that like to use humor, like Netflix or Taco Bell. They have to carefully calibrate how they translate their text (or not) into other languages, because what’s hilarious in English might fall flat in the target language or, worse yet, offend their audience.
Building a collaborative post-editing process by working directly with your post-editor sets you up for success (and makes the process easier when you’re ready to hire professional translation services).
At Smartling, you’ll get to know your translators through messaging tools like Slack, not only to provide feedback more efficiently, but also to get them to know your brand and messaging. The more familiar they are with your products and services.