The LSPs and Machine Translation: Why Not Treat MT as TM?
David Canek, MemSource Technologies Torben Dahl Jensen, Oversætterhuset MemSource Technologies
• Offshoot of a Charles University research project started in 2006 with Sun Microsystems • Develops Translation and Authoring Software: – MemSource Translation Server – MemSource Translation Cloud – UTMA Authoring Server • Headquartered in Prague Oversætterhuset / Translation House of Scandinavia • Leading Danish LSP with offices in Århus, Copenhagen and Kolding • Established in 1990 • Covers major European languages • Eager to explore new technologies to make the translation workflow more efficient Background
• The last LocWorld conference in Seattle covered MT deployments in Adobe, Autodesk and Cisco • Last year’s LocWorld in Berlin also covered primarily enterprise case studies on MT • What about LSPs and Machine Translation? We Will Explore
• MT deployment scenarios • MT quality assessment & monetization MT ADOPTION Who Got MT Technology First?
Enterprises? LSPs? Translators? Who Got MT Technology First?
Enterprises? LSPs? Translators?
1st: Translators Who Gets the Latest Technology First? Translators and MT
• MT Deployment: easy – uploading files to Google Translate costs just a little bit of time; and it is free • MT Monetization: trivial – MT simply speeds up their translations, so translators get more work done in less time Enterprises and MT
• MT Deployment: challenging – but have the resources to manage this • MT Monetization: complex – but being on the top of the food chain they have the power to renegotiate rates and drive home the MT- generated savings LSPs and MT
• MT Deployment: challenging – have limited resources and specific obstacles • MT Monetization: complex – will have to renegotiate translator rates to reflect MT savings MT Deployment in an LSP LSP Custom MT Development
• Considerable time and money to develop custom MT engine • Can easily end up with MT quality far inferior than the free online MT services • Specific obstacles: multiple domains and language pairs • Google spent millions of USD, has excess of 100 billion words of training data... A Scenario to Avoid
• LSP asks translator to post-edit a text machine translated by the LSP’s MT engine. • The quality is poor. Translator deletes the machine translation and instead uses GT, gets much better results... • On what basis can the LSP ask the translator to charge a reduced rate? Can LSPs Succeed with MT?
Yes. But do not necessarily start by developing a custom MT engine. Instead: • Begin using a readily available MT service • Measure its benefits • See if/how you are able to monetize the benefits • Only then explore the MT technology options BUSINESS CASE Building a Business Case for MT
(MT savings) minus (MT costs) = MT Profit MT Quality Measurement Today
Kirti Vashee MemSource MT Quality Measurement
• Simple, fast, precise • Extends the established translation memory analysis and discount schemes to machine translation
Why not treat MT just as another TM? How Does It Work Exactly?
• Traditional translation memory analysis – Document source segment vs. TM source segment
• MemSource machine translation analysis – Document target segment vs. MT target segment Translation Memory Match
Source Target Europarat TM MT Translation Memory Match
Source Target Europarat TM Europarat Council of Europe MT Translation Memory Match
100% Source Target Europarat TM Europarat Council of Europe MT Translation Memory Match
100% Source Target Europarat Council of Europe TM Europarat Council of Europe MT Machine Translation Match
Source Target Europarat TM MT Machine Translation Match
Source Target Europarat TM MT Europarat Council of Europe Machine Translation Match
Source Target 100% Europarat ? TM MT Europarat Council of Europe Machine Translation Match
Source Target 100% Europarat Council of Europe ? TM MT Europarat Council of Europe Machine Translation Match
Source Target 100% Europarat Council of Europe ✓ TM MT Europarat Council of Europe Analyzing MT Matches
Simply analyze MT matches and add them to the existing TM matches: Analyzing MT Matches
Simply analyze MT matches and add them to the existing TM matches: Analyzing MT Matches
Simply analyze MT matches and add them to the existing TM matches: Turning MT Matches into Money
Use your own discount scheme, e.g.:
TM Match % of Rate Paid New words 100% 75%-84% 50% 85%-94% 33% 95%-99% 25% 100% 10% Turning MT Matches into Money
...and add MT matches
TM & MT Matches % of Rate Paid New words 100% 75%-84% 50% 85%-94% 33% 95%-99% 25% 100% 10% Knowing Your MT Savings
When you know your MT savings, you can also better decide how much you can afford to pay for the MT service/technology. CASE STUDY RESULTS Case Study Overview
• Two LSPs participated • January – May 2011 • Domains: – Marketing – Law – EU – Technology Case Study Overview
• Language pairs: – English > Danish – English > Norwegian – English > Czech – Czech > English – English > German • Volume: 1 million words • Two MT engines: GT and a custom MT engine Case Study Results: Domain
MT Match Rate Legal Technology 0%-50% 73% 38% 50%-74% 17% 21% 75%-84% 5% 10% 85%-94% 2% 14% 95%-99% 1% 6% 100% 2% 11% Case Study Results: Language
MT Match Rate EN>CS EN>DE 0%-50% 72% 62% 50%-74% 14% 19% 75%-84% 6% 8% 85%-94% 3% 4% 95%-99% 2% 2% 100% 3% 5% Case Study Results: LSPs
MT Match Rate LSP1 LSP2 0%-50% 69% 63% 50%-74% 15% 18% 75%-84% 7% 6% 85%-94% 4% 5% 95%-99% 2% 3% 100% 3% 5% Next Steps
• Talking to translators and post-editors about the new approach • Negotiating TM/MT based discount schemes... THANK YOU