The dream of being able to automatically translate from one language to another is finally within our grasp. But just how effective is Machine Translation and is it really a viable alternative to human translation? In this post we aim to de-mystify Machine Translation by providing you with the information you need to decide whether Machine Translation might just be the solution you are looking for to help you save both time and money.
What is Machine Translation?
Also referred to as Automated Translation, Machine Translation is the process by which text is automatically transferred from one language to another using one or a combination of the following methods:
- Rule-based machine translation (RBMT) – uses language and grammar rules combined with specific dictionaries to generate translations.
- Statistical machine translation (SMT) – generates translations using statistical models created from the analysis of large databases of multilingual content (bilingual text corpora)
- Neural machine translation (NMT) – This relative newcomer gained traction in 2016 and uses deep learning based on neural networks to learn linguistic rules from statistical models, resulting in faster and better translations.
What level of quality can Machine Translation achieve?
The quality of Machine Translation output will depend on various factors:
- the configuration of the machine translation engine
- the quality of the source text
- the language combination
- the amount of previously translated material available
Because of these limitations, it is practically impossible for raw machine translation output to be used for any purpose that goes beyond that of “gisting” (basically trying to grasp the overall meaning of a text)
As a result, in recent years, the language service industry has adapted with the introduction of integrated processes for Machine Translation that combine automatic translation with human post-editing of machine translated text. In fact, this new skill is becoming increasingly requested.
How does Post-Editing of Machine Translation work?
The post-editing process is not dissimilar to revision in that precise rules need to be established in order to achieve the desired output. However this is a new skill for translators and therefore we have been focussing on providing training and guidance to our translators who are interested in specialising in this new discipline.
Generally, we adopt hybrid solutions for our customers that combine Machine Translation with Computer-Assisted Translation (i.e. Translation Memory Technology). In this scenario, results from the Translation Memory have priority and will be proposed to the translator when available, and the Machine Translation engine is used for new content.
In this way, the translator / post-editor is able to work within a familiar environment and reap the advantages of the combined technologies.
When it comes to offering Machine Translation with Post-Editing to our customers we generally propose the following service level:
MT with Full Post-Editing
This scenario is ideal for content that needs to be published and or widely distributed. The final output is comparable to that of a regular human translation. Usage cases include:
- Technical documentation
- Annual reports
For more information, please read our Machine Translation service page here.
What are the requirements for adopting Machine Translation?
Adopting an integrated Machine Translation process only makes sense for certain types of content. As a general rule, we only suggest Machine Translation solutions for technical content, as our experience with our types of content has not yet proved successful in terms of output quality and consequently savings in time and money.
What you can do to improve Machine Translation quality?
The overall savings and output quality of Machine Translation will depend on the quality and characteristics of the source text. If you follow a few simple guidelines, you should be able to optimize your Machine Translation to improve quality and savings:
- Keep your sentences short and ideally adopt controlled language
- Ensure you are using standard teminology
Potential Savings with Machine Translation
But how much can you save with Machine Translation? Contrary to what many people think, using Machine Translation will not remove your translation budget entirely (unless you just concentrate on using raw machine output for gisting purposes), however, depending on your specific situation you may be able to save between 30% and 50% of your translation budget.
Are you ready for the next step?
If you think your translation processes could benefit from Machine Translation solutions, contact us for a free consultation. Our experts will be able to advise on the suitability of your content, and provide suggestions for the best integrated translation workflow.