Chances are that most of us have some experience with machine translation in some way. Google Translate and similar tools have been around the web for quite some time. In fact, just yesterday I was using Google Translate because I sent a wedding gift to a friend in Spain, and received an email in Spanish - turns out they were having a problem with delivery!
Machine translation (MT) tools enable users to input their source-language text, and the engine will spit out a complete and mostly accurate (albeit quite literal) translation in the target language.
MT has been around for a bit longer than some may realize and the technology has come a long way from its origins. Modern machine learning and neural networks have pushed MT into an entirely new realm.
With usable and modern MT available, the question shouldn’t be if you decide to use MT, but rather, “when is the right time to use MT?”
Smartling Embraces Machine Translation
We recognize that not every job will require a human translator. That's why Smartling makes it easy for customers to find the path that works best for each project.
Smartling already connects with the most powerful and modern MT engines:
More recent innovations in this space is the advent of Neural Machine Translation. Neural machine translation (NMT) is designed to learn language much like the human brain does, adapting to your brand’s unique voice and tone overtime.
With direct integrations to leading providers, Smartling positions you to integrate with the best translation services possible.
But to understand how NMT has become so powerful, let's look a little bit further at exactly where MT came from, and how far it has evolved.
A Brief History of Machine Translation
The short story is this: MT stumbled first to become a usable solution, and was almost abandoned outright. Yet, modern tech break-throughs have awakened MT, specifically leveraging powerful neural networks for machine learning.
These are the four most prominent milestones of machine translations:
- 1949: MT started its infancy conceptually, with a physical device and public presentation finally making an appearance in 1954, by a Georgetown MT research team.
- 1966: The National Academy of Science formed a specific MT committee, known as ALPAC. A report published by ALPAC just a few years later almost decimated the industry, with strong suggestions to stop funding and for research to come to a halt -- the technology simply wasn't there to make it a possibility.
- 1997: MT makes its way into the mainstream as the internet takes off: AltaVista’s well-known Babelfish was introduced in '97, and Google Translate came to be almost 10 years later in '06.
- 2013: Modern MT starts to officially gain some ground, beginning with Statistical Translation. More recently, Google has been researching and implementing NMT.
Today we see NMT taking off, pushing the concept of MT into boundaries previously seen as impossible, at least according to ALPAC.
According to Jack Welde, Smartling Founder and CEO:
"Neural machine translation is gradually eliminating the demarcation between human and machine translation. It is creating more opportunities for a productive closed loop between machine and human, including machine enabled tools that make the human more productive, and human inputs that make the machine more accurate going forward.”
The Modern Forms of Machine Translation
For a quick high-level view, and to provide further context of how MT will fit into your business' strategy, let's take a closer look at the two major distinctions in modern MT -- Statistical and Neural Network based engines.
- Statistic Based engines learn through statistical analysis of a bilingual text, generally provided by the developer or user. These engines essentially develop an understanding of existing rules to determine the unique relationship between the source language and target language.
- Neural Based engines are the most modern approach to MT. Neural networks are designed to mimic how the human mind learns, gaining more knowledge over time. These engines seek to understand the context of what is being translated to properly predict the correct word choice.
Neural based engines are much more capable of capturing, and even understanding, the intent or meaning of a sentence, and therefore have been quickly replacing older statistical models. The idea here isn’t just swapping one word for another based on a rule or phrase.
Instead, the NMT engine is working to understand the intent behind your content in order to maintain and retain that particular message and tone in translation.
Out of the Box vs Adaptive
Part of the beauty behind modern NMT engines is the ability for not only rapid deployment but almost complete customization.
When leveraged as a service, most NMT engines can either be used straight out of the box -- but require in-depth training -- or can be pre-adapted for one specific brand or domain.
Training these engines alone can be a time-consuming process, but working with the right vendor can ensure not only quicker deployment, but also much more accurate results -- that is why Smartling offers integrations with the pioneers behind both neural networks and MT.
An adaptive NMT engine will constantly be growing its knowledge of your brand’s content, voice, tone and overall style to deliver localized content that still captures the exact presentation and quality experience unique to your brand.
When is MT the Right Choice?
Machine Translation is impressive technology and has come far from those early stages. Modern engines are now capable of competing with human translators, to a degree. In fact, we have a whole webinar dedicated explaining how content managers can incorporate MT into their translation process.
But in summary, when discussing MT we should be thinking along the lines of: "when do I hand off content to a human translator, and when do I let MT handle the task?"
The biggest factor will come down to content priority. Some complexities to consider might be:
- Where is this content going?
- What is the target audience?
- What demand is this content fulfilling?
- Can content be edited or revised after publication?
- Are there any legal restrictions or strict brand guidelines surrounding this content?
High priority critical content, for example legal documentation or medical information, will require the expertise of a human translator. Due to the nature of this content, and the high priority of accuracy, rapid deployment is not always be the main goal. One mistake could lead to a cascade of potential issues.
Even launching a new landing page for your latest product is a perfect example of high priority content: this is where brand voice and style needs to shine, and companies should look to leverage the creative touch of a human translator.
From there we can drill down even further and determine whether or not MT is the right choice for each project. This will heavily depend on the complexities involved. For example:
- Volume: If you are looking to translate as much content in as little time as possible, then MT can outpace human translators and bring otherwise massive projects into a more realistic time-table.
- Simplicity: When translating repetitive information, with clearly defined language and terminology, MT can handle the repetitive and simple text.
- Priority: Again, low priority content will be perfect for MT. For example, content that will be used internally might not require the same level of polish of a landing page for a new product.
It's as simple as asking yourself does this content make sense for machine translation? Do I need the creative input of a professional translator? Will I be able to correct my course of action, or once I hit send will that email exist, as it is, forever?
Finding the Right Process: MT Post Edit or Human One-Pass?
MT enables businesses to edge even closer to that perfect balance of moving content at a rapid pace and pushing to market as quickly as possible while reducing the time and capital spent on projects.
But, just because a project might fit into this criteria does not mean it will be ripe for MT -- and it doesn't mean that a human will never be involved in the process.
Whether or not the translation process will require internal review for every project is something that must be determined. In our experience, while content spends the most time during this process, only 4% of translations receive edits. So the question then becomes a determination of which path makes more sense:
- Should we rely on MT do the majority of the work and build in an internal check process with a human translator?
- Should we simply let a human handle the translation with an automated quality check working to ensure consistency throughout the process?
For example, translating user reviews of a product might seem like the perfect option.
- On one hand, there is a high volume of content, which is usually simple and repetitive, and might be too costly for a human translator.
- On the other hand, the priority for this content might be too high to rely on just a machine translation service; prospects rely heavily on user reviews, and these may be critical to specific use-cases.
One potential strategy here could be a mix of both human and MT, with professional translators focusing on the most important reviews, and MT handling smaller or less prominent reviews. Or, MT could be used to translate every single review, with a professional translated disclaimer at the top of the page highlighting this distinction.
The exact strategy to take will depend on the unique complexities and priorities of each individual business and project. That’s where Smartling fits right in.
Smartling Lets You Decide
Leveraging MT is more about balancing the content to move low priority, high volume content as fast as possible. This should, therefore, enable the human translators to focus on more important and crucial content.
With Smartling users can configure a Translation Workflow step to automatically assign content to the proper translation resource, whether that be a human translator or MT engine. Content can even be rejected, or assigned to a professional translator based on the complexity of the project.
For example, Lucidchart began leveraging Smartling to drastically improve their translation speed and agility, with the goal of rapid deployment to match their fast release cycles. Previous translation methods couldn’t keep up and were slowing down the entire roadmap.
By injecting NMT into the process, Lucidchart can provide a consistent and cohesive localized product experience to their international users, without any negative impact on their product and release cycle.
With machine translation, Lucidchart managed to drop their translation time from 2 days to a mere 10 minutes, supporting their rapid release schedule. Smartling’s professional translators can then replace or update any content at a later date if necessary.
The important part here is how flexible the platform can be. Smartling already provides deep integration with the numerous engines listed above, and will only continue to grow our automation functionality by helping users find the right MT service for their exact needs.
Where Will MT Go From Here?
In summary, MT has made huge strides since the very early days. Even 10 years back, with Google Translate pushing the concept mainstream, MT was far from perfect.
Modern solutions leveraging powerful machine learning are constantly pushing new boundaries and will only continue to improve overtime as their knowledge grows. However, there will always be a need for a personal touch at some point, and automation will not entirely replace human translators.
When it comes to localization, you’re going to be faced with this question: should I use machine translation?
Human translators are the ones that will provide that extra level of creativity for the highest quality of work. Machine translation is all about getting the job done with a margin for error.
Want to chat with an expert? Give us a call, Smartling is here to help you move the world with words.
Matt Grech is the Content Marketing Manager at Smartling, responsible for growing Smartling awareness and brand content. As a digital content writer, Matt applies his journalistic lens to content, helping users deepen their understanding of the brand, services and technology provided by Smartling. Matt has previously contributed to an industry leading Unified Communications resource, as well as local newspapers where he developed his unique ability to investigate, interview, and transform complex problems into simple solutions.