by Chris Durand
Machine translation is the use of software to translate text from one language to another, usually without assistance from a human translator. It is a fascinating field that is changing rapidly, but here’s my take on where things stand today.
Machine translation is cheap, and it is getting better every day. I was encouraged by the success of IBM’s Jeopardy-playing system Watson in drubbing its human challengers. Watson’s ability to “understand” idioms and natural language will contribute greatly to the future of machine translation.
Translation projects vary in requirements for accuracy as shown in the following diagram. For projects jobs where accuracy is less important, machine translation is a workable alternative. An example of this would be a company support forum, with huge amounts of user-supplied content. It is not cost-effective to pay a human translator to translate every post by a user into numerous languages. However, a machine translation engine that has been tuned to translate support issues for a particular product won’t create perfect results, but may still be a valuable resource to users. And creating value is what translation is all about.
Of course there are many translation jobs where accuracy is critical, such as legal documents. And translations of literature, poetry, and the like will remain difficult for machine translation software for years since there is much more to this sort of translation than accuracy, such as style and other artistic considerations.
But with continuing advances in computing and linguistics, the line shown in the above diagram will move steadily to the right over time.
Given the high variability of machine translation results (read: really bad translation), human translators still must review the results, reducing the cost advantage of machine translation. Some customers try to save money by running their material though a generic translation service like Google Translate and taking the results to human translators to “clean up”. Don’t bother. It’s usually cheaper to just let skilled translators do the job from scratch if you want a good translation.
Bad translations create a number of problems, such as damaging your brand and resulting in unhappy users. Would you buy a blender from a company if the box had a bunch of obvious translation mistakes on it? If they don’t care enough to get a professional translation done for their product, what does that say about the company’s commitment to quality?
And remember that paragraph or link text on your website that you forgot to get translated? You know, the one you just ran through Google Translate and are about to post to your website hoping no one will notice? Don’t. Can you identify an obvious error in Chinese? Or Arabic? Which brings us to…
It’s not hard to imagine catastrophic outcomes from bad machine translation, but here are two humorous examples:
- From the Department of Not Recognizing Machine Translation Errors, we have the “Translation Server Error” café in China. This is legendary in translation circles. Apparently the owners of the café were thoughtful enough to translate their restaurant name from Chinese to English. Unfortunately, the online translation server they used was not working properly, and they printed up a bright, new sign with the English name “Translation Server Error”. (Though they probably got far more publicity out of their failed translation than if a professional translator had done the job correctly, so perhaps this is not a gaffe at all.)
Years ago my father-in-law was taking a French class and had to write a short introduction of himself to the class (in French). To check his work, he pasted his French about how his grandson Hans lives in Portland into an online translation site to check his work, and got back the following:
Our only grandson, Grunts, also lives has Portland.
We still call my nephew Grunts to this day.
Categories: A World View, Translation | Tags: Bridge360, Chris Durand, Global Business, Internationalization, Localization, Machine Translation, Translation | Permalink.
Software Changes Everything.... Bridge360 improves and develops custom application software. We specialize in solving complex problems at every phase of the software development lifecycle, removing roadblocks to help our clients’ software and applications reach their full potential in any market. The Bridge360 customer base includes software companies and world technology leaders, leading system integrators, federal and state government agencies, and small to enterprise businesses across the globe. Clients spanning industries from legal to healthcare, automotive to energy, and high tech to high fashion count on us to clear a path for success. Bridge360 was founded in 2001 (as Austin Test) and is headquartered in Austin, Texas with offices in Beijing, China.
About the service
The eTranslation service provides the ability to translate formatted documents and plain text between any pair of EU official languages, as well as Icelandic and Norwegian (Bokmål), while preserving to the greatest extent possible the structure and format of those documents.
CEF eTranslation builds on the European Commission’s earlier machine translation service, MT@EC, which was developed by the Directorate-General for Translation (DGT) under the Interoperability Solutions for European Public Administrations (ISA) programme. It was based on MOSES open-source translation toolkit, a Statistical Machine Translation (SMT) system developed with co-funding from EU research and innovation programmes, while eTranslation is following the field’s move into neural machine translation.
Both systems are trained using the vast Euramis translation memories, comprising over 1 billion sentences in the 24 official EU languages produced by the translators of the EU institutions over the past decades. As such, they are particularly suited for the needs of EU policy documents.
CEF eTranslation carries on the MT@EC functionalities and scales-up the existing infrastructure by improving quality and performance and increasing the pool of available language resources.
Learn more about how it works
Ready to get started?
eTranslation can be used in two distinct ways:
1. One-off translations
It provides a web user interface for direct use by individuals (human-to-machine use).
2. Integrated automated translation functionality
It provides machine translation capabilities for digital services through an API (Application Programming Interface) (machine-to-machine use).
Users of the service
The CEF Machine Translation service is intended for the following type of users:
- Service providers: European and national public administrations interested in integrating machine translation in their digital services to guarantee their services are supported in all the official languages of the EU.
- Translators in EU institutions and in national public administrations interested in finding out how machine translation can facilitate their day-to-day work and cross-border information exchange.
- Other staff: non-translating staff in EU institutions and in national public administrations interested in finding out how machine translation can facilitate their day-to-day work and cross-border information exchange.
Benefits of the service
For officials, particularly translators, in EU and national public administrations using CEF eTranslation:
- Supports the work of translators, reducing the burden of routine translation and enabling them to focus on very specific or important sections of documents
- Increases the speed with which incoming documents can be translated, understood and routed when necessary
- Facilitates easier information exchange between parties based on their expertise, rather than on the knowledge of the working language(s) of the group
- Available free of charge until at least the end of 2020
For public administrations and cross-border EU projects integrating CEF eTranslation into their digital services:
- Widens the potential customer base of the service by lowering language barriers
- Improves the customer experience by giving end users of the service the freedom to interact with it in the language of their choosing
- Increases the speed with which documents are handled
- Lowers costs by reducing reliance on human translation
For European citizens and businesses
- Gives citizens and businesses the confidence to benefit from a wider range of digital public services in Europe, regardless of their language ability