Machine Translation Engines

Not every Machine Translation engine is right for you. Here’s how we evaluate best fit.

Category: Technology, Translation Services

There are plenty of Machine Translation engine choices available to you once you decide that Machine Translation (MT) is a good fit for your professional translation project. And each type of engine can help speed up the translation process with varying degrees of translation quality.

But not every machine is the right choice for every translation job. That’s where Acclaro’s expertise comes in. We can partner with you to select and deploy the right type of MT engine depending on your content, target languages and subject matter. Since we are a platform neutral consultant and are not under any pressure to push a certain MT solution to our clients, we only recommend those engines that fit our clients’ quality, turnaround time and budget requirements.

Types of Machine Translation Engines

There are different MT platforms available and each is based on a type of MT engine. The “smarter” machines have created a wide variety of options for professional MT projects. But while MT has improved with advancements in neural MT for example, the machine can’t do all the work on its own. So what options exist and for what types of content? MT has produced satisfactory results for lower visibility content like internal documents for translations in established languages. But professional linguists still play a massive role in getting your content translated with the appropriate level of quality. Let’s take a look at the pros and cons of different types of MT engines Acclaro might recommend and use:

    • Uncustomized, “out of the box” neural MT engines — This type of MT engine works best if you’re  looking for “generic” translations and have no or few specific brand, style, terminology requirements and preferences. If you have established guidelines and preferences for your brand voice/tone, terminology and style, customizing the MT engine is essential to “teach” it what those preferences are.
    • Customized Neural MT Engines — This type of engine can provide high-quality translations. It allows the translated material to sound more human-like and can provide translations that are more fluent. The technology allows it to fully capture the context of the material better.
    • Statistical MT Engines — These type of engines can be taught, but may need several rounds of initial training to achieve satisfactory output. They also need to be retrained at regular intervals.
    • Adaptive MT Engines — These engines learn “on the fly” and take less time to get started with. This is typically a good fit for large projects that use relatively new content and that require a large team of linguists. The MT engine learns in real-time from the interaction and choices made by the linguists and adapts the suggestions accordingly.

Evaluating MT Engine Output

When thinking about using MT for a project, you have some factors to consider. Acclaro has deep knowledge and experience of MT platforms and when we evaluate MT options with a client, we determine the most important factors first — the desired quality, turnaround time and budget.

1. Define quality, turnaround time and budget expectations upfront

Can all engines handle all types of jobs? Unfortunately, the answer is no. Like experts in their fields, certain MT engines are better suited for certain types of translation projects. That’s why we work with clients to clearly define project requirements and quality expectations upfront. This way we can help strike a good balance between cost and time savings on the one hand, and quality on the other.

2. Evaluate content

Certain types of lower-level content where a basic understanding of the source content is sufficient, for example instructions or internal documents, might be a good fit for fully automated useful translation (FAUT). With this type of MT, there is typically little human intervention. While MT engines are still trained and carefully set up in this scenario, once the MT output is considered to be satisfactory, the output is used as-is without any post-editing by human linguists.

Other MT projects with higher visibility or where accuracy is key may require post-editing by highly specialized human linguists. These linguists have deep subject matter knowledge, and review the source and target content to resolve issues with accuracy, terminology, style, etc. Despite the vast improvements in MT, assigning the right job to the right team of linguists is still as important as with human-only translation to ensure the best possible translation quality.

3. Adaptive MT vs. post-editing approach

There’s a lot to evaluate when considering what MT engine is the best fit. Since we work with MT for a wide variety of clients, we have processes in place to evaluate what MT engine is the best option for you. How do we do this? We review your project and match it up with the best engine to help you get your desired outcome. This includes evaluating engines based on an adaptive vs. post-editing approach. For well-established statistical or neural MT engines, post-editing can be a very efficient way to produce the desired translation quality utilizing the machine and human translators. Adaptive MT places more emphasis on human involvement. With adaptive MT, the MT suggestions are generated  interactively so the linguist can accept all or part of the MT output in real-time.

There are many nuances to take into consideration when selecting MT engines. One of the benefits of working with Acclaro is our experience in this area. We evaluate whether it would be best to use post-editing in combination with neural or statistical engines, for example. Or, we can help you understand whether an adaptive approach, done in real-time with an MT engine and a translator, can accomplish your goals.

4. MT Engine training for quality improvements

We are able to customize MT engines by evaluating whether relevant, existing translations can be used to “train” engines for a new project. As mentioned earlier, MT engines can be trained in one of two ways:

          1. Use previously translated content that is stored in a Translation Memory database, as well as glossaries and monolingual data to train the MT engine.
          2. Via live translation using adaptive MT.

Before training and customizing MT engines, we recommend and can help clients establish guidelines and preferences for brand voice and tone, terminology and style for the target languages. A well-trained engine produces higher quality results since it’s preloaded with your desired terminology and style so less time needs to be spent on post-editing, resulting in cost savings.

5. Automated vs. human evaluation

Once we’ve reviewed content and client considerations around quality, turnaround time and budget, we evaluate output from MT engines that may be a good fit for the job. We work closely with clients during this process to ensure quality needs are met. There are a number of ways we can evaluate the quality of the MT engine output, including comparing it to a human translation.

          • BLEU Scores – One common method used in the translation industry is the BLEU (bilingual evaluation understudy) score. BLEU uses an algorithm to compare a machine translation and a human translation and looks at how similar the human and machine translations are.
          • Human Evaluation – Another method we use is to have a linguist score the MT output. The linguist can compare the output of multiple MT engines and give qualitative feedback. This method allows us to understand if there are issues with the system like recurring mistakes for example.

Ultimately, human evaluation of your project and the capabilities of each machine will allow us to select the best engine type for you based on text, language and subject matter. Our evaluation is based off our prior experience using the machine in our work with others. Sometimes, we’ll suggest a combination of engines for a given project to provide you with the desired output at the best cost available for each target language.

MT Client Success Stories

Acclaro has worked with a number of clients to help them get the best MT results. Each company faced a unique situation. Through our expertise with MT, each was able to get the results they were looking for.

Machine translation for support documents

A software client wanted to test out the need for additional languages for support documents. The goal is to provide a cost-effective way to translate content using MT and post-editing. The content is to be published on the website to test acceptance and interest. This user feedback will be used to build a business case for adding additional target languages and to define the desired translation quality level.

Machine translation for online customer support content

One of our long-standing clients –  an analytics company that sells software and hardware in a number of different industries – asked us to partner with them on finding and deploying the best MT option without sacrificing quality for its customer support and help content. We supported them for many years with human translations but due to turnaround and budget requirements, they decided to explore MT options.

In collaboration with the client, we opted for a rule-based MT engine initially and as MT evolved, we deployed a statistical MT engine that supports Asian languages, produces better quality output, and requires less set-up time. In addition to quality improvements produced by the statistical MT engine, we ensure quality needs are met by deploying a full post-editing step by a linguist to eliminate grammatical errors and incorrect translations and by customizing the MT engine with existing, previously translated content.

To further improve translation quality, we’re currently exploring a customized, neural MT engine for this client.

Machine translation for eCommerce content

An eCommerce client, with a need to translate a large volume of words on an aggressive timeline, turned to us to help them evaluate and deploy MT. The client requirements included error-free translations of product descriptions with less strict rules around terminology, tone and style.

Since we had no translation memory available to us for the tricky language combination, Korean to Traditional Chinese, we opted for a neural MT engine to first translate the Korean content into English, and then from  English to Traditional Chinese. After the first pilot round we re-evaluated the MT engine output and were then able to set up a customized engine for this client to further improve translation quality.

Work with an expert translation partner to help you find the right MT approach

What will work for you? That’s a great question and one that we look forward to answering. Know that we work with a number of different MT engines and stay on top of the latest developments so we can introduce our clients to the best solution for their needs.

Don’t be overwhelmed with the many factors that you need to consider when making a decision. Acclaro is a trusted provider to many companies looking to benefit from MT. We can help you evaluate the engines that best meet your needs and provide quality translations so your project is successfully completed  — on time and within budget.