This is a past event. Please join us for the upcoming conference.
ru uk

Kirti Vashee

VP of Enterprise Translation sales for Asia Online

Kirti was previously responsible for the worldwide marketing and business development strategy at Language Weaver. He has long-term software industry experience (EMC, Legato, Dow Jones, Lotus) and has been involved in building and managing sales and support operations in Europe and Asia for several software companies. He is the moderator of the Automated Language Translation (MT) group with over 4000 members in LinkedIn and also a board member of AMTA (American Machine Translation Association). Kirti is active on Twitter (@kvashee) and the blogosphere on MT ( ) and translation automation related issues. He received his formal education in South Africa, India and the United States. He is also an amateur musician who plays the sitar, bansuri and guitar.

Understanding MT ROI & Best Practices

This presentation will describe the various approaches to Machine Translation and outline the ROI characteristics of these approaches available in the market today. It will also cover:

  • The MT output quality impact on ROI -- As it has become easier to build MT engines many have overlooked the relationship between MT output quality and ROI and the fact that only MT systems that produce high quality output give you positive ROI.
  • Critical skills required to develop high quality MT systems as this is a process rather than an instant black box solution. The session will explore the type of expertise and overview the evolutionary process required to get the best results.
  • Rapid and accurate MT quality assessment strategies. To best determine if MT is useful to a professional translation production process, it is very important to understand the quality level of each unique MT system as this has implications in post-production processes and overall delivered quality. This ability to assess the actual properties of the system you are dealing with is important, both for individual translators and agencies.
  • Case studies of some MT initiatives to contrast and overview critical trade-offs. This includes an understanding of where you are most likely to get high ROI, what to do if there is not enough data, how to build terminological consistency, new kinds of linguistic analysis that helps engines develop and improve faster. Some specific issues and strategies related to Slavic languages will also be covered.
  • Effective post-editing and PEMT compensation strategies describing some different approaches and contrast early experiences that created strong resistance from translators to more recent win-win scenarios that are efficient, effective and fair. Various strategies used to get more translator involvement are also examined.