{"id":460,"date":"2022-10-31T12:20:15","date_gmt":"2022-10-31T12:20:15","guid":{"rendered":"https:\/\/www.ata-divisions.org\/LTD\/?p=460"},"modified":"2026-03-14T19:15:36","modified_gmt":"2026-03-14T19:15:36","slug":"mtpe-nqsf","status":"publish","type":"post","link":"https:\/\/www.ata-divisions.org\/LTD\/mtpe-nqsf\/","title":{"rendered":"MTPE? nQsf!"},"content":{"rendered":"

By Bridget Hylak, Administrator, Language Technology Division<\/em><\/p>\n

Linguists old and new are celebrating and\/or struggling with the influx of project requests requiring MT or MTPE. Like it or hate it, neither one is going anywhere. Mind you, though, they are two very different things.<\/p>\n

MT, or machine translation, is an undeniable and oh-so-handy tool for linguists to have in their professional toolbox. Depending on the language combination and specialty you work in, and the specific engine you choose (there are many, so research optimal engines for your combo), MT can become your new favorite, furry friend. <\/p>\n

If you haven\u2019t tried it yet, or haven\u2019t securely incorporated it into your professional work environment, reach out your hand already and take the olive branch. MT won\u2019t bite or upset your flow; it will purr like a kitty and lick your feet, well, also like a kitty. <\/p>\n

If pets aren\u2019t your thing, just think of your first car as a young adult \u2013 smelling the smells, caressing the steering wheel, turning up the music and feeling an undeniable sense of newfound freedom.<\/p>\n

In other words, if you haven\u2019t quite cozied up to MT in your daily grind yet, where have you been all my life? Give me a call (WhatsApp also works), we need to talk.<\/p>\n

Yep, it\u2019s that good.<\/p>\n

While some less common, lower-resource languages are still in the process of building truly useful engines, don\u2019t worry. The world\u2019s getting smaller by the minute, MT is only getting better at learning, and your day will come. To anyone in that situation, you have my heartfelt apologies that the powers that be haven\u2019t yet done their due diligence. In the meantime, keep playing around with it until you start to notice, \u201cHey, that\u2019s not bad\u2026\u201d<\/p>\n

MTPE, or machine translation post-editing, on the other hand, isn\u2019t exactly the same thing and shouldn\u2019t (yet) be discussed in the same Zoom webinar. <\/p>\n

When it comes to MTPE, my current philosophy is simple: MTPE nQsf.<\/p>\n

Huh?<\/p>\n

That\u2019s, \u201cMTPE, not QUITE so fast\u2026\u201d<\/p>\n

Think of MTPE this way:<\/p>\n

MT = machine
\nPE = you<\/p>\n

Successful, highly accurate MTPE requires special handling by a trained linguist who, at first, might find themself completely flabbergasted by the task. MTPE is not like regular \u201cE,\u201d that is, editing the work of a trained, competent colleague. Nor is MTPE anything like \u201cT,\u201d that is, translation with MT in the background. Neither does it represent merely a linguistic challenge, but a technical one as well.<\/p>\n

But wait! You didn\u2019t become a translator to use technology, you say? You didn\u2019t spend all those years mastering foreign language XYZ only to have a machine cramp your style? Tell that to the neurosurgeon currently conducting robotic brain surgeries, or the auto mechanic who hooks incoming cars up to the hard drive to diagnose and resolve issues. Nowadays, and even \u201cway-back-then-adays,\u201d both professionals need not only industry smarts, but tech prowess, too. That is, if they want to keep their jobs.<\/p>\n

My favorite analogy which erupted over my own frustration with communicating both the promise and the pain of language technology is that of a surgical robot. I\u2019ve shared this illustration on countless occasions to both linguist, client and government audiences, and the silence that immediately falls makes it clear that a loud, clangy bell has rung somewhere in their heads. <\/p>\n

It goes like this. If you are on the operating table about to go under for a right radical nephrectomy (\u201cthe old fashioned way\u201d), and the pre-op nurse casually mentions that your surgeon will be using a robot, whoa, Nellie! How would you respond?<\/p>\n

Personally, I would demand to know three things, then two more (so five all together, I guess\u2026 the mental math is still intact):<\/p>\n