What is Machine Translation Gisting?
By United Language Group
Machine Translation (MT) can be a daunting subject with its multiple training approaches and long list of terms. Those new to MT can easily get confused when words like SMT, corpus, preprocessing and post editing are thrown around.
One such term is “gisting.” It’s brought up frequently and is a huge part of how MT is used, but what does it really mean, and what do you need to know about how it’s used?
When Should and Shouldn’t You Gist?
Simply put, gisting is the use of MT to translate foreign text to get an understanding of the original content’s meaning. To do this, the translation doesn’t need to be perfect. It just needs to translate the general meaning of the foreign text.
Gisting is an excellent way to translate several types of content, such as internal company communications, contracts, RFPs and other forms. When foreign text is encountered in any of these content types, gisting comes in handy because the translated material doesn’t need to be 100 percent accurate to be useful.
When gisting is used for external company content, problems quickly become apparent. Since gisting results in roughshod translations, it can quickly devolve into confusing mistranslations, especially if the MT hasn’t been trained on industry-specific terms.
Gisting isn’t enough when you need a quality translation, especially when the content you’re translating will be outward-facing. In these situations, it’s usually better to go with human translators.
Gisting and Data Security
Many services offer open source MT solutions for users, and gisting is regularly used. Google Translate is the most common method of gisting, and is a tempting option because it’s easy and free to use.
Nevertheless, there are issues to using open-source options to gist internal company documents. Data security is a significant part of any business, but there are those that take company material and put it into a free translation service, assuming it’s completely safe.
That’s not the case. Open source MT is free, but once the data is processed, it’s no longer yours.
If you try and get the gist of a foreign coworker’s email and it turns out to contain confidential information, suddenly you have a data security problem on your hands if you used free translation. The same can happen if a law firm tries to use free translation programs for foreign documents during the eDiscovery process.
Now more than ever, data security has become a pressing issue, and companies can’t afford to lose data, even through a seemingly innocent incident of gisting using an open-source translation service. Laws like the General Data Protection Regulation (GDPR) will soon levy heavy fines for data loss.
Gisting with Secure Machine Translation
The answer to these data security issues is secure MT. In addition to avoiding potentially illegal data loss, the MT can be trained to industry-specific terminology and jargon, making gisting an even more useful option for internal company content.
One such secure MT solution is OctaveMT Powered by Lucy – our newest solution for security conscious users who need a modular, rapid approach to document, website, and text translation projects.
Gisting is supposed to be quick, easy, and cheap. There are pitfalls to getting free gisting of company content; you’ll have to ask yourself if the risk is worth it.
ULG’s insights delivered straight to your inbox.
Thoughtful editorials from industry experts delivered weekly in bite-sized pieces.