
Translators without Borders is a nonprofit organization based in the U.S. that “aims to close the language gaps that hinder critical humanitarian and development efforts worldwide.” The organization maintains a global network of professional translators who volunteer their services to provide aid in humanitarian crisis response. The efforts of TWB are worthwhile mentioning in more than one respect, but sticking to the theme of this column—translation technology—I’ll report on exactly that in relation to TWB. But first, here are some numbers that may illustrate the far reach of TWB.
There are presently over 4,000 registered translators worldwide in the TWB Workspace, a platform where a wide range of nonprofit and aid organizations approved by TWB can request translations, and where TWB translators can accept and deliver the work on a pro bono basis. There is also a much smaller group of “rapid-response translators” registered on the site. (The platform was developed and donated by ProZ, but you can still use Workspace even if you’re not a ProZ member.) TWB works in approximately 190 language pairs and has translated 43 million words so far (10 million in 2016). Some of the hot spots in which TWB has been involved include the European and Burundi refugee crises, the earthquakes in Nepal and Haiti, the typhoon in the Philippines, and the Ebola and Zika outbreaks.
I talked with Mirko Plitt, who joined TWB as the head of technology in June 2016, about what technology TWB is using and why things in that area may have been moving a little more slowly than if the organization were a commercial entity.
Mirko says that for years TWB worked like a non-governmental organization (NGO), rushing from crisis to crisis, each with a different set of parameters and requirements. This resulted in essentially no time to stop and streamline technological efforts, even with the basic tools that many of us take for granted, such as a shared translation memory.
The efforts of Translators without Borders are worthwhile mentioning in more than one respect, including those related to translation technology.
It wasn’t that solutions were unavailable. In fact, many translation technology companies had offered free access to their technology (“free” as in “no monetary compensation,” but not necessarily in “no public relations benefits”), so it wasn’t finances that stood in the way. Instead, the organization needed to hire a dedicated specialist (who turned out to be Mirko). This person would not necessarily be subject to the ongoing operations, but would be specifically in charge of developing the technological framework for translation and other language-related tasks.
This is where things stand at the moment. Mirko has developed Kató, which is a customized version of the same system on which Matecat is based. (Kató is named after Kató Lomb, one of the first simultaneous interpreters.) This system was chosen because: a) it was open-source and, therefore, customizable without having to rely on the technology vendor; b) it was easy to use without the need for specialized training; and c) it could be used by virtually anyone, professional translator or not. Kató, in connection with the TWB Workspace, now enables partners (TWB lingo for NGO clients) to upload translatable documents in MS Word, PowerPoint, OpenOffice, and text formats. (A project manager has to be involved for other formats.) Translators in the right language combination accept and translate the documents while using the language resources of MyMemory (a mixture of contributed translation memory resources, aligned materials, and machine-translated data), if those are available. They can then store and share translation memory data with other TWB translators in an otherwise private translation memory.
Since the documents are often too large for individual translators to work on, they can be split into as many parts as desired. Translators working on different parts of the documents can communicate with each other through a chat feature. Editors (or other personnel) can work on the documents simultaneously, allowing for a very quick turnaround of often mission-critical information.
These are not TWB’s only recent technological achievements. It has, for instance, been involved in the development of a glossary app that consists of audio snippets in various languages that can be used by aid workers. (These snippets can be recorded within Kató.) An application programming interface (API) for Kató was published so that it can be integrated into other systems. In addition, TWB recently launched machine translation systems for Kurmanji (Northern Kurdish) and Sorani (Central Kurdish), which are the main languages for Kurdish refugees. I was particularly intrigued with the Kurdish machine translation solution. Neither of those languages had existing workable offline solutions, so Prompsit, a language technology company, took three weeks to prepare an open-source rules-based machine translation system (Apertium) and prep it for the training of Kurmanji and Sorani. The company then guided 10 Kurdish translators for a week via Skype for the data and rules entry.
Can we expect great results from that engine? Linguistically speaking, I would say likely not. But from a humanitarian perspective? No doubt.
There are other aspects aside from humanitarian that I found meaningful when talking to Mirko. As Mirko noted correctly, the technological gap between languages has increased even more just this year. Neural machine translation has propelled languages that are deemed as “more important” into a territory that seems unreachable for the other 99+% of languages. It’s organizations like TWB who try to give some of those languages a technological underpinning that they’re unlikely to get elsewhere.
If you’re interested in contributing your talents to TWB, you can find information about becoming a volunteer right here (www.translatorswithoutborders.org/volunteer).
Apertium
www.apertium.org
Kató
https://ts.translatorswithoutborders.org
MyMemory
www.mymemory.translated.net
Prompsit
www.prompsit.com
Translators without Borders
www.translatorswithoutborders.org/volunteer
TWB Workspace
http://bit.ly/TWB-Workspace
Jost Zetzsche is the co-author of Found in Translation: How Language Shapes Our Lives and Transforms the World, a robust source for replenishing your arsenal of information about how human translation and machine translation each play an important part in the broader world of translation. Contact: jzetzsche@internationalwriters.com.
This column has two goals: to inform the community about technological advances and to encourage the use and appreciation of technology among translation professionals.