Go global with this Winning Combination – Content strategy and Machine Translation
Download as PPTX, PDF0 likes183 views
The webinar discusses the integration of machine translation (MT) within content strategy, focusing on adapting MT for various content types and improving translator productivity. Key objectives include enhancing translation efficiency and quality through customizable and scalable MT systems like KantanMT. Case studies highlight successful implementations in technical manuals and online help, resulting in significant cost savings and productivity increases.
Go global with this Winning Combination – Content strategy and Machine Translation
- 1. Content Strategy and Machine Translation The Winning Combination
- 2. Webinar Content The Prize What can be achieved with MT MT & The Content Strategy How content strategy can be adapted for MT Q&A 40 minutes
- 3. The Prize
- 4. What is KantanMT? Statistical Custom MT Platform Cloud-based Extremely customisable Highly scalable for high volume Fully-automated translations High speed, high quality translations Active KantanMT Engines 9,392 Training Words Uploaded 434,189,753,677 Member Words Translated 7,161,269,925 KantanMT
- 6. Software Industry. Objectives Build MT engines for on-line help Pilot for English => German Scale to multiple target languages Focus on Translator productivity Challenges Complexity of online help content Very tight production schedules Pilot & Other Languages < 4 months
- 7. Software Industry. Results Highly Scalable: +4 languages in 6 months High Quality Translation output Translator Productivity Increase: 30-50% Reduced Project Costs: 27-40% savings Lower Post-Edit Rates after KantanMT Engine Retraining Case Study available for download.
- 9. Technical Manuals Objectives Languages: English->Dutch POC to validate rapid ROI Focus on translation productivity Solution must scale to 50 manuals pa. Integrate to existing L10N workflow Challenges Client had already built in-house MT Output of in-house system very poor
- 10. Technical Manuals Results Seamless integration into existing L10N workflow Translation productivity: + 25% Reduced Post-Editing effort using PEX Reduced project turnaround time Significantly higher quality translations achieved Process will scale to meet future requirements Case Study available for download.
- 11. MT & Content Strategy
- 12. Strategic Decisions High Level Business Needs - Create a ‘Global Model’ Structural Elements What content? Where is it needed? What are the differences? Governance Elements How will it be managed?
- 13. Strategic Decisions – where? = 3 billion people
- 14. What Languages? Government of India – Hindi in the Devanagari script plus English Indian constitution lists 22 recognised languages 2001 Census – 122 major languages and 1,599 other languages Also recorded 30 languages spoken by more than 1m people
- 15. Education Levels? Adult Literacy Rate, 15+ both sexes. Source: Worldbank World Average Philippines India China Indonesia Nigeria
- 16. In Thailand for instance? Official government survey : Average amount of reading by respondents – 7 sentences per year. Website experience - No use of ‘more info’ button No product descriptions Use of imagery and video Think about how best to present the information
- 17. Structural Model and MT What Content What Locales and Languages? What Content Types? Sharing, Differences, Transcreation? MT? It’s the needs of the business that influence these decisions. Make the decisions and then review the process for MT fit.
- 18. Governance Model and MT Centralised Federated Hybrid • One MT system makes sense to generate economies of learning across management and users. (Unless that provider cannot service the locale/domain.) • Cloud based solutions can be accessed from anywhere! • Leverage local language/domain expertise if required
- 19. Getting Tactical about Content for MT Shorter sentences Remove needless words Be consistent Use glossaries Avoid idioms and jargon Use correct grammar Controlled Language Identify Named Entities Stick to Unicode Standard - UTF8
- 20. Get serious about TMs MT depends on Training data Cleanse your TMs Training data can help to: Improve precision – bi-lingual Improve fluency – mono-lingual Maintain consistency – glossaries Library data and pre-built engines* can help to supplement data. (*KantanLibrary™ & KantanFleet™)
- 21. How is Quality Determined Automated scores Build Analytics Linguistic Quality Review But ultimately: The customer decides!! Build in your own kpis
- 22. Thank You.
Editor's Notes
- #3: No more expensive deployments Monthly subscription plan Customised subscription plan No more complexity KantanMT does all the heavy lifting You focus on what you do best – grow and develop your business
- #5: No more expensive deployments Monthly subscription plan Customised subscription plan No more complexity KantanMT does all the heavy lifting You focus on what you do best – grow and develop your business
- #13: You all have probably heard these first two much quoted stats but it’s worth revisiting them. This has been supported by a more recent study into cross border internet selling by the Uni of Amsterdam. The point of course is that language is as much a challenge to communication in the connected world as it was in the offline world So what about the fast growing, faster developing markets?
- #14: The chart show the real growth in median income on the vertical axis and the projected median income on the horizontal axis. So for these countries the median income is expected to grow at a rate of between 45% and 90% over the next 15 years. What’s even more interesting is that these 5 markets account for a combined population of over 3 billion So where does that leave us with regards the language challenge?
- #15: The government of India cites Hindi and English as the official government languages and of course English is taught in secondary school But there are 22 what they call scheduled languages in the Indian constitution 122 major languages and over one and a half thousand other languages Now the challenge here is what is the ‘preferred’ language of your target audience and do we need to use that to communicate most effectively?
- #16: Also, if we do need to communicate in English or their preferred language is literacy an issue? The chart from the Worldbank show the official level of literacy reported for each country Taking these at face value they seem pretty good with three of the countries above the world average. However….