blog.inten.to Open in urlscan Pro
52.4.240.221  Public Scan

Form analysis
0 forms found in the DOM

Text Content

Open in app

Sign In

Get started


Home
Notifications
Lists
Stories

--------------------------------------------------------------------------------

Write




RESPONSES (1)



What are your thoughts?

Cancel
Respond

Also publish to my profile

There are currently no responses for this story.

Be the first to respond.

Published in

Intento

James Hjerpe
Follow

May 6

·
3 min read
·

Listen



Save







MACHINE TRANSLATION ROI: HOW SUBWAY SAVED $1.5M AND 2 YEARS OF LABOR USING
INTENTO’S BEST-FIT MT



At the XTMLive 2022 conference last week in Silicon Valley, Carrie Fischer
(Manager of Globalization Services, Subway) was joined by Mark Hjerpe (Head of
Revenue, Intento) and Rory Sampair (Solutions Architect, XTM) to discuss the
clear, measurable returns delivered by machine translation. The panelists
addressed (among others) the question most people have when approaching MT: is
it possible to save a bunch of money and time while still maintaining quality?
After Carrie’s first year using Intento’s best-fit MT solutions, the answer was
a resounding yes, as outlined below.



At Intento, we find that customers typically have too much content, and not
enough human translators. They can only translate around 5% of their needed
content with their human resources. For the other 95%, you really need to employ
machine automation (machine translation and machine voice, in Subway’s case).
This is especially true when you have a surplus of translation requests coming
in from a mix of different departments, in a variety of content types, and
requiring multiple languages.


MASSIVE KNOWLEDGE-BASE TRANSLATION

Fischer had been experimenting with MT for Subway’s content for years and was
never convinced that it was a viable solution. That was until she saw a demo of
Intento’s MT management platform, MT Hub. Beneath the complex formulas and
algorithms was a simple, clear result — around 90% of the output was coming back
with high levels of quality.

> After seeing her first demo of Intento MT Hub, Carrie’s response was: “This is
> exactly what I’ve been waiting for.”

When Fischer was tasked with translating 700 knowledge-base articles into 4
languages in a tight time frame, she turned to Intento’s MT solutions. With
machine translation, she was able to meet the narrow deadline with high-quality
results.


FRANCHISE WEBSITE TRANSLATION

The second project on her hands was a franchisee sales website. They essentially
wanted to automate how a franchisee could buy their franchise. It ended up being
a 500,000-word project, with a deadline of 2 weeks. A different use case — but
the same high-quality results were delivered through Intento’s curated MT
solution.

> After using Intento MT for a year in multiple use cases, Carrie was given the
> best review of her career and saved $1.5 million and two full years of labor
> in the process.


E-LEARNING VOICE SYNTHESIS AND TRANSLATION

The final use case, which never struck Fischer as an MT opportunity, was
e-learning content. During the beginning of the COVID-19 pandemic, many
businesses, including Subway, had to digitize at an extremely fast pace. The
usual learning pace for onboarding franchisees was a two-week in-person course.
That suddenly became out of the question. They immediately transformed the
course into several e-learning modules and curated several MT models with the
best-fit providers for their language pairs. This use case included utilizing
voice synthesis (machine voice), which was produced with the same exceptional
results. Just as Intento evaluates, selects, and customizes the best fit MT
engines, they do the same curation method with machine voice engines, with
results and cost and time savings that speak for themselves — literally.


USE-CASES FOR LEGAL DEPARTMENTS AND BEYOND

With machine translation and machine voice success under her belt, Fischer is
confidently expanding her MT use at Subway, including Intento MT Hub for Office
Productivity. This plug-in is for products like Microsoft Excel, Microsoft Word,
Google Chrome, and more. MT Hub for Office Productivity facilitates several
internal use cases for Subway, including the instant translation of legal
documents. It has evolved to the point where Fischer’s team is so happy with the
MT output of Office Productivity that they’ve started to use it globally for
contract translation and legal communication, freeing up a lot of room in their
budgets.

Subway’s reliance on Intento for MT/AI program development is one of the many
examples of Intento clients that begin by selecting and training a number of
engines for their most pressing business needs, and then, wowed by the quality
and time and effort savings, begin spreading the success and ROI around their
company. Get a live demo at https://inten.to/demo/ to see how Intento can add
value to your own translation program.




1



1





MORE FROM INTENTO

Follow

Intento Enterprise AI Hub is a gateway enabling global companies to unlock the
full potential of AI for creative processes, increasing productivity by 20X.

Grigory Sapunov

·May 1


OPENAI AND THE ROAD TO TEXT-GUIDED IMAGE GENERATION: DALL·E, CLIP, GLIDE, DALL·E
2 (UNCLIP)

OpenAI recently announced their DALL·E 2 system capable of creating images based
on a textual description. It’s the second version of the system, and the first
one was published nearly a year ago. …

Deep Learning

21 min read





--------------------------------------------------------------------------------

Share your ideas with millions of readers.

Write on Medium

--------------------------------------------------------------------------------

James Hjerpe

·Apr 15


MARCH 2022: BUILD A WORLD-CLASS MT PROGRAM, THE NEW ROLE OF LOCALIZATION
MANAGERS, AND MORE

Jump into Spring with a look at Intento services to help you build a world-class
machine translation program, the new role of localization managers in the
corporate landscape, measurable returns delivered by machine translation, and
more. 🌎 MT Evaluation and Maintenance for a world-class translation program 🤖
Simplified navigation in…

Machine Translation

5 min read





--------------------------------------------------------------------------------

James Hjerpe

·Mar 18


THE ELEVATION OF THE LOCALIZATION MANAGER IN THE DIGITAL ERA

In the last couple of years, we’ve seen the volume of global content skyrocket,
teams scattered across the globe, and CEOs using terms like ‘massively
multilingual’, and ‘AI-driven global content strategy’. Sitting in the eye of
this digital storm, loc managers are in a unique position of elevated importance
to…

Localization

6 min read





--------------------------------------------------------------------------------

Konstantin Savenkov

·Mar 16


DOES MACHINE TRANSLATION SUPPORT KYIV?

In the real world, Kyiv won over Kiev in Wikipedia and all other major style
guides — but most Machine Translation engines aren’t there yet. Russia invaded
Ukraine on February 24, 2022 — and since then, the war has remained at the
forefront of all our minds. You may not…

Machine Translation

2 min read





--------------------------------------------------------------------------------

James Hjerpe

·Mar 4


FEBRUARY 2022: ASSISTANCE TO UKRAINIAN REFUGEES, THREE NEW MT STUDIO FEATURES TO
STREAMLINE YOUR WORKFLOW, AND MORE!

With the situation unfolding in Europe, we want to lead off this month by
highlighting our latest initiative to assist Ukrainian refugees throughout the
EU who are in urgent need of translation services. If you require any document
translation, including scans and photos (or know someone who might), we’ll
grant…

AI

4 min read





--------------------------------------------------------------------------------

Read more from Intento


RECOMMENDED FROM MEDIUM

Hiranmaya Gundu

in

MiQ Tech and Analytics

TESTCONTAINERS: THE MODERN WAY OF WRITING DATABASE TESTS



Antón Garcia

in

Abraia

VIDEO TRANSCODING AND OPTIMIZATION FOR WEB WITH FFMPEG MADE EASY



Evan Li

ARDUINO FOR ELEMENTARY STUDENTS CHAPTER 1:



Volkan Nazmi Metin

in

CloudBoost

RISE OF FUNCTIONAL PROGRAMMING



Totalcloud.io

in

FAUN Publication

GETTING A HANDLE ON SPIRALLING AWS LAMBDA COST IN SECONDS



Sri hastuti

CARA INSTALASI DAN PENERAPAN NEXT-AUTH PADA NEXT.JS



Vitor Balbio

C# CODE SNIPPET — INVOKEREPEATING IN GODOT



Ethan Rosenrauch

RECONCILING FINANCIAL DATA WITH PYTHON PANDAS



AboutHelpTermsPrivacy

--------------------------------------------------------------------------------


GET THE MEDIUM APP


Get started

Sign In


JAMES HJERPE


18 Followers


Follow



MORE FROM MEDIUM

James Hjerpe

in

Intento

LOCALIZATION CHECKUP: MT EFFICACY AND POST-EDITING PERFORMANCE ANALYSIS



Davorin Gradecak

in

Photomath Engineering

PHOTOMATH’S BIGGEST CLOUD AND INFRASTRUCTURE MISTAKES, AND HOW WE FIXED THEM



Tochukwu Nwoke

DEPLOY HUGGING FACE MODEL AT SCALE QUICKLY AND SEAMLESSLY USING SYNDICAI



Piotr Celej

in

stepstone-tech-blog

IS IT NEEDED FOR DEVS TO KNOW COMPANY MISSION?



Help

Status

Writers

Blog

Careers

Privacy

Terms

About

Knowable

To make Medium work, we log user data. By using Medium, you agree to our Privacy
Policy, including cookie policy.