Tag: neural machine translation

Post-editing of Machine Translation: Negotiating Projects

Within a project of post-editing of machine translation (PEMT), the requisites and expectations will vary depending on the different stakeholders. The enterprise customer that turns to the freelance translator/post-editor will do so for reasons that are different or in contrast with those for which he could turn to an LSP. Likewise, an LSP which turns to freelancers for post-editing does so with different requisites and with a different scope than the one with which the freelancer will see his/her assignment.

Read More »

Writing for Machine Translation

The quality of an MT engine raw output and the final results after post-editing depend on various factors, one of which is the quality of source content. For this reason, the pre-editing stage of a text is as important as the post-editing.

Read More »

How to Survive Technological Hypes

This article was originally published on the WordBee Blog. Neural networks, neural machine translation, speech-to-speech technology, blockchain, translator implants in our brains, automated interpreting, mind reading

Read More »

[Guest Post] The Need For MT Evaluation

After I published my review of Slate Desktop few weeks ago, I received some interesting comments. Is GNMT really better than a Slate engine? Why build a SMT engine when NMT is already available? …. and other questions. I have a post planned about all this as soon as possible. 
I have kept my test of Slate Desktop as basic and as quick as possible to see if it was really simple to build an SMT engine.  But of course, the devil is in the details. So, I invited Tom Hoar, Slate’s CEO, to give a more technical overview of what needs to be taken into account when building and evaluating your own engine. We also agreed on a test to see who was the best: Slate or GNMT. You can read it in the guest post

Read More »

SmartReads

Sign up for my monthly
#SmartReads on the Translation Industry



    Your email is safe with me and I will never share it with anyone.

    Search

    Archives