TAUS MT Showcase, Sovee Smart Engine 2.0, A Leap Beyond Base Moses Technology, Scott Gaskill, Sovee
•
1 like•1,198 views
The document summarizes a presentation given by Scott Gaskill and Christopher Klapp on June 4th, 2014 about Sovee's Smart Engine 2.0 machine translation technology. The presentation discusses how Smart Engine 2.0 provides significant improvements over traditional Moses-based statistical machine translation, including the ability to continuously learn and improve translations in real-time from user feedback. It also notes how translation will increasingly become an essential utility embedded in many applications and devices as internet access expands globally.
Recommended
More Related Content
Viewers also liked
Viewers also liked (14)
Similar to TAUS MT Showcase, Sovee Smart Engine 2.0, A Leap Beyond Base Moses Technology, Scott Gaskill, Sovee
Similar to TAUS MT Showcase, Sovee Smart Engine 2.0, A Leap Beyond Base Moses Technology, Scott Gaskill, Sovee (20)
More from TAUS - The Language Data Network
More from TAUS - The Language Data Network (20)
Recently uploaded
Recently uploaded (20)
TAUS MT Showcase, Sovee Smart Engine 2.0, A Leap Beyond Base Moses Technology, Scott Gaskill, Sovee
- 1. Wednesday, 4 June Sovee Smart Engine 2.0: A Leap Beyond Base Moses Technology Sco$ Gaskill, Sovee TAUS Machine TranslaDon Showcase 2014 Dublin (Ireland) The research within the project MosesCore leading to these results has received funding from the European Union 7th Framework Programme, grant agreement no 288487
- 2. Presented by: Scott Gaskill Christopher Klapp June 4, 2014 MT Showcase
- 3. 3 I skate to where the puck is going to be, not where it has been. Wayne Gretzsky, Hockey Star
- 4. 4 Where is the world going? CNNTech, “Google boss: EnDre world will be online by 2020,” April 2013 hXp://www.cnn.com/2013/04/15/tech/web/eric-‐schmidt-‐internet Kenya stat from ITU, 2-‐13. Photo used by permission of Deseret News. 2016 the world will have internet connecDvity By the end of this decade everyone in the world will be on the Web, with Mobile access growing as the preferred interface In Kenya, 99% of Internet connecDons are mobile
- 5. 5 We are entering the Convergence era: translaDon will be a uDlity embedded in every app, device and screen. Businesses will prosper by finding new customers in new markets…. Consumers will become world-‐wise, communicaDng as if language barriers never existed. Jaap van der Meer, Director of TAUS, 2013
- 6. 6 Transla9on Memory – Is More Be?er? If we simply add an addiDonal 1,000 TM lines to a database of 40-‐60 billion, will we see beXer translaDons? Knowing how to use the data is key
- 7. 7 Challenges Technology, approach & process Progress in first 60 years Progress Needed by 2016 Engines for < 150 Languages Engines for > 6000 languages < 3% of the world’s content translated All content translated Cloud-‐based speed providing more servers for translaDon 92 billion Servers StaDsDcal translaDon introduced, but “fuzzy logic” does not deliver quality businesses need Quality improvement to standards required to meet world commerce demand
- 8. 8 4 ( n(n-‐1) 2 ) Generic SMT 92 million 9.2 billion – based on 100 businesses 92 billion Based on 1000 customers Not valued as pracDcal – infinite servers required MT Assets (cascades) Technology Challenge 6800 languages Generic SMT Domain Generic SMT Domain Customer Generic SMT Domain Customer Project Minimum Server Requirements
- 9. 9 Accuracy Challenge Relevant Segments General Corpus Adequacy Accuracy General MT (30-‐40%) TM (40-‐60%) Post EdiDng (up to 100%)
- 10. Preparing new project / import TM / CAT Leverage Exact Fuzzy Match Post Edit Review Deliver to customer Gather past TM Package and send TM to SMT provider Clean, tokenize, data (prepare data) Train –Tune-‐Test (3Ts) Repeat unDl viewed as acceptable (repeat with customer data each Dme) 10 Post Edi9ng Learning Engine SMT Workflow Segments are not just a string of text – they are a living learning en99es Process Real-time Automation and Integration Sovee Smart Engine 2.0
- 11. 11 Smart Engine Advantages Language from Scratch Seamless integra9on to Post Edi9ng workflow Training / Learning Efficiency Gains (what we have seen) Post ediDng – 50%+ improvement TM /MT management and training – 100% improvement Update MT on the fly Watch it learn before your eyes Never leave the post ediDng environment
- 12. 12 Learned Transla9ons !"#"$%&'()"*+"&',( -"&".%#((/0.12,(( 34"52%67( 3662.%67( -"&".%#(89( :0+%;&( (<.*%&;=%>0&( /2,'0+".( ?.0@"6'( 3,,"'( 9%*,( Cascading Assets Sovee Smart Engine MT Learned Segments Segment output
- 13. 1 2 Asset Synchrony (CAT Tools) Post edi9ng interface Smart Engine 13 Asset Push (Past TM) Real-‐9me progressive transla9on cycle (Sovee MT, save /push post edits) 1 2
- 14. 14 Demo
- 15. 15 Seamless Integra9on “Convergence Era” Apps Websites eCommerce elearning Videos Podcasts Sorware Live chat Text Messages email
- 16. Japan Sovee Smart Engine TranslaDon USA Yukiko (Japan): ホールインワンを決めたよ！ Robert (USA): I just scored a hole-‐in-‐one! Original: ホールインワンを決めたよ！ Japan SNAG
- 17. 17 Jack Nicklaus Learning Leagues Languages: Spanish and Japanese In Process: 10 more languages Video and Training Materials for Golf Instruc9on
- 18. 18 R.E. Michel
- 19. 19 Ques9ons?