O slideshow foi denunciado.
Utilizamos seu perfil e dados de atividades no LinkedIn para personalizar e exibir anúncios mais relevantes. Altere suas preferências de anúncios quando desejar.
What? Why? How?
Factors that impact the success of
commercial MT projects
John Tinsley
Iconic Translation Machines
AMTA – ...
Why MT?
• Speed
• Cost savings
• Time to market
• Your competitors are
doing it!
“Why would I need MT?”
Why Now?
• volume ...
“What type of MT is it?”
• The goal of the MT here is to be good enough so that - on the
whole – with TMs, translators are faster post-editing some...
• The goal is to produce MT that’s fit for a particular purpose as
is
• Arguably easier from an MT development perspective...
Butterfly Effect
Quality
Required
Integratio
n Needs
TM
Leverage
Buyer
Maturity
Training
Data
Languag
e
Volume
Content
The 8 Factors influe...
Language
Not all languages are created equal
French German Turkish Finnish
Spanish Chinese Korean Hungarian
Portuguese Jap...
Volume
Not all languages are created equal
The more words…the better…the worse?
Content Type
The bed was two twin beds put together and
me and my girlfriend kept fallin in the middle
(since we like to c...
Training Data
Corpora. Dictionaries. Terminology.
MT experience
Little experience A lot of experience
Har
d
“Easy”
LSP/vendor
experience with MT
Ease of
adoption
The more e...
Integration requirements
Standard vs Custom Integration
“instant” solution costs rise
proportionality with the number of
l...
TM Leverage
High TM
Leverage
Low MT
Effectiveness
Matches # words
Context 403,803
100% 585,459
95-99% 50,366
85-94% 41,604...
Quality requirements
• Fully automatic human quality
• 300% post-editing productivity
• French to Spanish == English to Ko...
Quality
Required
Integratio
n Needs
TM
Leverage
Buyer
Maturity
Training
Data
Languag
e
Volume
Content
The 8 Factors influe...
• “What volume of words do you estimate for the project?”
• “Do we have translation memories, glossaries that are
relevant...
“How much
training data do I
need?”
“How frequently
can I retrain the
engine?”
“What happens
to my data?”“Do you do
langua...
Próximos SlideShares
Carregando em…5
×

What? Why? How? Factors that impact the success of commercial MT projects

263 visualizações

Publicada em

This was a presentation given at the conference of the Association of Machine Translation in the Americas (AMTA) in Austin, Texas on October 31st, 2016. This is a predominantly academic event, and this presentation was a condensed version of our "MT Success Blog Series" on our website where we aimed to give the community and idea as to the practical considerations around commercial machine translation.

http://iconictranslation.com/2016/07/8-steps-to-mt-success-series-introduction/

Publicada em: Tecnologia
  • Seja o primeiro a comentar

  • Seja a primeira pessoa a gostar disto

What? Why? How? Factors that impact the success of commercial MT projects

  1. 1. What? Why? How? Factors that impact the success of commercial MT projects John Tinsley Iconic Translation Machines AMTA – Austin, Texas – October 2016
  2. 2. Why MT? • Speed • Cost savings • Time to market • Your competitors are doing it! “Why would I need MT?” Why Now? • volume of content is growing • demand, more words less time • growth facilitator • #FOMO – you’re missing out on business What’s the MT value proposition?
  3. 3. “What type of MT is it?”
  4. 4. • The goal of the MT here is to be good enough so that - on the whole – with TMs, translators are faster post-editing some segments • Challenges – development has to focus on reducing needs for edits, not necessarily anything else – translator acceptance always a big barrier – evaluation can take time and has many factors – pricing models How are companies using MT? What are the use cases for MT? Translator productivity through post-editing
  5. 5. • The goal is to produce MT that’s fit for a particular purpose as is • Arguably easier from an MT development perspective • Often high-volumes = more achievable How are companies using MT? What are the use cases for MT? MT for information
  6. 6. Butterfly Effect
  7. 7. Quality Required Integratio n Needs TM Leverage Buyer Maturity Training Data Languag e Volume Content The 8 Factors influencing MT suitability High TM Leverage Low MT Effectiveness
  8. 8. Language Not all languages are created equal French German Turkish Finnish Spanish Chinese Korean Hungarian Portuguese Japanese Thai Basque
  9. 9. Volume Not all languages are created equal The more words…the better…the worse?
  10. 10. Content Type The bed was two twin beds put together and me and my girlfriend kept fallin in the middle (since we like to cuddle) and that was iritating Late nite room service was awesome Social Media User Generated Content Highly Technical Marketing, Nuanced
  11. 11. Training Data Corpora. Dictionaries. Terminology.
  12. 12. MT experience Little experience A lot of experience Har d “Easy” LSP/vendor experience with MT Ease of adoption The more experience the LSP has with onboarding/training vendors, and the more experience the vendor has with MT, the more feasible the adoption of MT will be
  13. 13. Integration requirements Standard vs Custom Integration “instant” solution costs rise proportionality with the number of languages and the throughput needs
  14. 14. TM Leverage High TM Leverage Low MT Effectiveness Matches # words Context 403,803 100% 585,459 95-99% 50,366 85-94% 41,604 75-84% 32,319 50-74% 18,972 No Match 81,119 Total 1,213,643 Only 8% of all words go to MT
  15. 15. Quality requirements • Fully automatic human quality • 300% post-editing productivity • French to Spanish == English to Korean • Best performance out of the box
  16. 16. Quality Required Integratio n Needs TM Leverage Buyer Maturity Training Data Languag e Volume Content The 8 Factors influencing MT suitability High TM Leverage Low MT Effectiveness
  17. 17. • “What volume of words do you estimate for the project?” • “Do we have translation memories, glossaries that are relevant? Can we create them?” • “If so, what leverage are we getting?” • “To we have post-editors? Access to a supply chain?” – “what experience do they have?” • “Where will MT fit in the workflow (depending on the use case)?” • “What variety is there in the content that the MT will be processing?” • “Why aren’t you using Google Translate?” • “Is there sufficient budget for this project?” What questions should YOU be asking?
  18. 18. “How much training data do I need?” “How frequently can I retrain the engine?” “What happens to my data?”“Do you do language X?” “How good is the quality?” “How do you measure performance over time?” john@iconictranslation.com www.iconictranslation.com @iconictrans

×