"Introducing MT. An LSP workflow"

by Elena Murgolo, Aglatech14

Update: the event has now finished (Feb 19th 2021).


Have you ever wondered how MT is deployed in an LSP? How do they choose it and test it?

Typically, LSPs are not exactly end-users: the real end-users are either professional translators who need to post-edit MT output or non-language professionals who use it in their daily life, sometimes without even realizing it, as in social media. Language service providers and translation companies find themselves between developers and end-users. But they are also among the most likely to implement costly solutions, such as trained engines, hosting, and subscriptions, to be able to use cutting-edge technology and high-quality products. LSPs are also probably the owners of the best data to be used during training and creation of new systems. Implementing this relatively new technology, however, presents new challenges together with the numerous advantages. In this talk I will summarize the process and give an overview of what an LSP might be facing when approaching MT and PE and our suggestions based on lessons we learned.

Speaker’s bio

After graduating in Conference Interpreting and working a couple of years as simultaneous and liaison interpreter in fairs and events, Elena Murgolo began working in Aglatech14 as technical translator for German and English. She led the Post-Editing department of the company, and is now Language Technology Team Lead, managing Language Technology deployment and use within the LSP. She and her team are responsible for centralizing and developing LT expertise within the company and with external resources, including freelance translators, vendors, clients, and partner universities. She is also involved in training new resources in the field of MT, PE, CAT tools and Language Technology in general.


University of Wolverhampton
Wulfruna Street
Wolverhampton, WV1 1LY
United Kingdom