5 Effective Strategies for Post-Editing MT
Because of the misleading fluency of NMT systems, we now have to get the meaning of the source text first and then compare the text with the MT raw output to make sure that the translation is correct and adequate.Good to know that there are still people who realize that advocating for "Monolingual Post-Editing", as some zealots increasingly do is ever more dangerous, especially now that machine translation is becoming even more "fluent".
Edit:
The link was not correct but it should work now.
Link in a post is not work "5 Effective Strategies for Post-Editing MT"
ReplyDeleteFixed: thank you for pointing out he error
DeleteVery interesting, thanks for sharing that with us!
ReplyDeleteWhether we like it or not, Post-editing MT is here to stay. I'm not pessimistic about it. I see a future where man and machine work together much more productively, joining the best of both of them. Let's wait and see:-D
ReplyDelete