When does using machine translation make sense?

Machine translation (MT) gets a lot of attention. But, even as machine learning, engine performance and quality improves, many questions still surround MT and its suitability for various translation needs.

• Do these tools work equally well across all languages?
• How well does MT translate creative, technical or eCommerce content?
• Can MT be used effectively in a professional setting for business content?

Weighing the pros and cons

Whether or not MT is a smart option generally depends on language requirements and the type and volume of your content. There are many MT options available — from open source to proprietary vendors. Some are free and others require significant investment.

With advice from an expert translation partner, you can make an informed decision and implement the MT approach that’s best for you. Using MT when it’s well-suited to your content is a worthwhile investment. It allows you to save money, speed up the translation process and decrease your time to market.

When deciding if MT is right for your translation initiative, you’ll want to weigh cost, speed and quality. Your choice will also depend on what content types you need to translate. You’ll also need to answer the question: “What are your quality expectations for each different type of content?”

To figure out what’s best for you, let’s start by understanding the different types of MT used today. Some technologies are older and some are new, but each has a specific place in the translation landscape.

Five types of machine translation and how they work

Machine translation was first used in the 1950s. Since then, multiple developments have propelled the technology forward to help get better quality translations.

Before we get started, it may be helpful to reference our guide to machine translation terminology as you read below.

Now, let’s take a look at the five different types of machine translation.

1. Rule-based machine translation (RBMT)

Rule-based MT is a collection of “rules” governing the use of language. These rules, developed by linguists, help the machine translate from the source language to the target language. A good example here is a rule that helps the machine correctly translate the formal and informal version of “you” in German. Although this type of MT was the first commercially available, the technology is no longer widely commercially in use.

2. Statistical machine translation (SMT)

Statistical MT uses algorithms to produce millions of possible permutations, and selects the text that appears to be the best translation. Like rule-based MT, statistical MT is no longer widely used.

Why? Because it takes a lot of effort to maintain the system and translation quality is relatively low. However, both systems are now blended together into hybrid systems, which improves translation quality.

3. Hybrid machine translation (HMT)

Hybrid MT combines rule-based and statistical MT. Using translation memory (TM), hybrid MT can deliver consistent quality. However, hybrid MT can also require extensive human post-editing by a qualified linguist.

4. Neural machine translation (NMT)

A breakthrough for MT came in 2016 when Google introduced neural MT. Using a neural network, artificial intelligence (AI), modeled on the human brain, neural MT predicts the most likely word sequence.

To learn more, here’s an in-depth look into the evolution of neural machine translation.

5. Adaptive machine translation (AMT)

Another innovative development in 2016 came with the development of adaptive MT. Here, translators interact with MT suggestions — effectively training the MT engine in real time.

As it’s trained, the MT engine learns new terms and phrases in the right context, and can even learn your brand’s tone and voice. This allows neural MT to result in higher quality translations. MT platform providers can further optimize MT engines for speed, quality, and budget for large-scale localization initiatives.

Is MT a good option for you and your content?

When used effectively, MT is usually faster than human translation. This typically creates efficiencies that can lead to faster deliveries and lower costs.

The key is to realize that not every piece of content is a good fit for MT. Sometimes, a human linguist will produce the best result. Other times, MT and a human linguist can work together to deliver exactly what you need.

MT can handle many different types of content. So when you need to decide if MT can work for your content, it’s important to consider several factors. Each type of machine translation has pros and cons.

As MT technology has developed, a common challenge has been a binary use/don’t use perspective. But when used properly, MT can be integrated into your translation tools and processes. In essence, MT can act as a real-time assistant to the professional linguist and accelerate high-quality human translations.

Keep in mind, the type of content you need to translate will ultimately drive the decision of whether to use MT or not. A good rule of thumb is: the higher the content’s value, the more likely you’ll need a human linguist.

Let’s look at some examples to help make this clear.

MT for FAQs and other knowledge base content

Machine translation is a good fit when you need basic communication and understanding. MT can assist human linguists to translate content types like: customer support content and eCommerce content, including product descriptions, FAQs and technical documentation.

These content types generally only need to inform, and don’t have the nuances of more creative content. Also, the content is not as visible as, say, marketing content. In other words, the goal is communication, not perfection.

Often, human edited or even “raw” MT is a good fit for content that wouldn’t otherwise be translated because of budget and time constraints. We typically recommend including an MT approach when clients need to translate well-structured, informational content (often consisting of millions of words).

MT for legal and similar content where accuracy is key

Accuracy is extremely important for legal documents, product packaging, apps and user dashboards. The obvious translation approach is usually to opt for a human linguist. But, early on in the process, adaptive MT integrated into computer aided translation (CAT) or translation memory (TM) tools can play a helpful role. These tools can speed up the translation process for the linguist.

Getting the click with creative and marketing content

When you need to capture accuracy and nuance, a human linguist is key. Content like marketing campaigns, website copy, emails, sales presentations, videos, etc. need a high level of cultural and technical accuracy. A human linguist is the best approach to correctly translate this type of content, so we don’t recommend MT.

A human linguist should also do most, if not all, of the translation for content types like SEO, pay-per-click ads and landing pages.

The future of machine translation

In the 1960s, available MT systems were inaccurate and expensive compared to human translations. While technology has come a long way, even today MT has limitations and potential for errors. Even so, MT has rapidly become an important part of the professional translation industry.

The technology is awe-inspiring and will only push further ahead. With MT, translation can happen faster than ever before, speeding up time to market. And developments like neural machine translation from Google and Microsoft continue to make machines ever more useful for businesses.

Neural MT can understand the similarities of words, consider entire sentences and “learn” complex relationships between languages. Fluency (proper grammar and readability) has come a long way in neural MT. Accuracy is better as well, but still requires thorough post-editing. A human linguist can work in tandem with neural MT to start the translation process, then fine tune for a finished product.

Even so, neural MT does have some drawbacks. A large one is that strong neural engines have a limited amount of language combinations. In the coming years, engines will add more language combinations and streamline even more translations.

To go deeper into this subject, read our analysis on the next big challenges for neural machine translation.

How we assess if MT is a good fit for you

We work closely with our clients to identify when MT makes sense for them. Here’s how we help our clients select the MT approach that best fits their goals, needs, budget and content.

1. Requirements analysis

In this first step, we evaluate your content volume and type(s), language pair(s), quality expectations and privacy requirements.

2. Content analysis

Here, we assess if your source text is suitable for MT from a technical and linguistic perspective. This includes file types, structure and formatting.

3. MT platform evaluation

Based on the first two steps, we evaluate what MT platform is best suited for your localization initiative. This may include an MT output evaluation where we apply machine translations from several platforms and review and evaluate the output.

4. MT custom engine development

In some cases, we’ll opt to create a custom neural MT solution. We only recommend this option when we know that it will outperform all other MT platforms for the type of content that you need to translate.

We can either create this completely from scratch, or we can create a custom solution on top of one of the best available neural MT systems. First, we gather and prepare a large collection of bilingual data and adapt the content to your specific domain. Later, we’ll choose the latest and best technology available to train a state of the art MT solution, completely unique and customized to your needs and content.

Partner with machine translation experts

With experience across many MT platforms and a holistic tech approach, we work closely with our clients to identify when machine translation makes sense for them. If you’re considering machine translation and would like to evaluate your options, check out our machine translation services.