TAUS MACHINE TRANSLATION SHOWCASE Google Translator Toolkit 14:20 – 14:40 Wednesday, 10 April 2013 Patcharin Areewong Google
Jul 03, 2015
TAUS MACHINE TRANSLATION SHOWCASE
Google Translator Toolkit 14:20 – 14:40 Wednesday, 10 April 2013 Patcharin Areewong Google
Google Confidential and Proprietary 2
Machine Translation
Patcharin Areewong Language Specialist • Singapore
Google Confidential and Proprietary
Agenda
• Introduction
• Google translate
• Google translator toolkit
• Demo
3
Google Confidential and Proprietary
“Organize the world's information and make it universally accessible and useful.”
Translation is the key to universal access
你好 こんにちは
!लो
hallo
hola
olá
hello
bonjour
привет
jambo
ممررححبباا
mhoroi
kiana
napaykullayki
4
Google Confidential and Proprietary
A translator’s story… 5
Translator 2,000 words per day
250 days per year 500,000 words per year
Google Confidential and Proprietary
The Google story… 6
Google 1,000,000,000 new pages indexed
per year* 400 words per page
400,000,000,000 words per year
* actually, it’s several billion pages but let’s round it down to 1 billion
400B/0.5M=800,000 translators
and that’s for only
1 additional language!
Google Confidential and Proprietary
So much content! So little resource! 7
Organize the world’s information and make it universally accessible and useful.
http://www.commonsenseadvisory.com/Resources/FactsandFigures/tabid/1213/Default.aspx
>50% of Google searches come from outside the United States. Localized search in more than 55 countries, 35 languages.
Google UI available in 117 languages across 157 international domains.
Madar research, 2007
8% of world population speaks Arabic. Only 1% of the web is in Arabic.
>99% of what people write, say, or generate never leaves the language in which it was created.
Google Confidential and Proprietary
8
Google Confidential and Proprietary
Google Confidential
9
Machine translation is better than nothing
• Handle overwhelming volume
• Provide Immediate turn-around
• No access to human translator
• Users are one click away from inaccessible content
9
Google Confidential and Proprietary
Drive demand for human translation 10
If you talk to a man in a language he understands, that goes to his head. If you talk to him in his language, that goes to his heart.
– Nelson Mandela
Variable Value Customer demand 1 vs. 10 Revenue per customer €10 vs. €100
MT experiment can measure customer demand, profitability. If the content is proved valuable, it’s worth the human translation price
Google Confidential and Proprietary
Expand translation industry
Human translation expensive for content with uncertain value • If 10 readers, expensive to pay $10,000 for translation
• If 100,000 readers, $10,000 translation worth the price
Monitor adoption, feedback • Human-translate inscrutable content: offensive, misleading
• Human-translate high-traffic content: worth the price
11
Bottom line: - Quick experiments - Low cost
Google Confidential and Proprietary
Target users: amateurs and advanced translators Languages: 100,000+ pairs
MT languages: 88 (includes variants)
UI languages: 36
File types: AdWords, HTML, TXT, PO, Android App, Chrome Extension, RTF, subtitles, Word, ODT
General features: WYSIWYG editor, sharing, chat, spell check, publish to Google Docs
Advanced features: translation memory, glossary, Google dictionary, label, concordance, scoping, split/merge, repetition
12
Google Confidential and Proprietary
Google: open translation ecosystem 13
Google translation follows “data liberation” principle • Support open standards, APIs
Data stored in Translator Toolkit is your data – not Google’s • Cloud storage for access, scale
• Documents, glossaries, and TMs for your eyes only unless you share
• You control addition, deletion of your translations
How can you be big without being evil? We don’t trap end users. So if you don’t like Google, if for whatever reason we do a bad job for you, we make it easy for you to move to our competitor.
– Eric Schmidt data liberation!
Google Confidential and Proprietary
14
Demo Time!
Google Confidential and Proprietary
Try it today at http://translate.google.com/toolkit
15
Google Confidential and Proprietary
Questions?
16