This site uses cookies.
Some of these cookies are essential to the operation of the site,
while others help to improve your experience by providing insights into how the site is being used.
For more information, please see the ProZ.com privacy policy.
ProZ/TV The interpreter's journey: Building resilience, finding renewal
A virtual conference dedicated to the evolving world of interpreting in 2026.
At its heart, the event is about interpreters finding fresh strength, refining their path, staying on the loop of AI advances, and reconnecting with purpose.
Click the Session tab to access
recordings of the full schedule including, panel discussions and presentations
Take advantage of the available discounts on the $avings tab including special pricing on Software and ProZ.com membership (available for new
members only)
Discussion for SDL Translation Technology Insights (2016)
Altaf Hussain Пакистан Local time: 18:47 англиски на урду + ...
Superb and useful
Jun 21, 2016
The event was very much useful, which added in my knowledge as professional translator
Christian Romeo NJIA
Subject:
Comment:
The contents of this post will automatically be included in the ticket generated. Please add any additional comments or explanation (optional)
lugoben Local time: 09:47 англиски на шпански + ...
chunking of phrases
Jun 21, 2016
It is a way that is being considered in research. It consists in breaking up the phrase in little parts called chunks. I didn't quite understand how the lack of context in this technique, was going to circumvent the context problem. I expected that some approach of improving MT's accuracy would be the way to go. Chunking is done to improve throughput. Along with it, there has to be others part of the translation task would need to be improved also, to keep the overall productivity. Interested i... See more
It is a way that is being considered in research. It consists in breaking up the phrase in little parts called chunks. I didn't quite understand how the lack of context in this technique, was going to circumvent the context problem. I expected that some approach of improving MT's accuracy would be the way to go. Chunking is done to improve throughput. Along with it, there has to be others part of the translation task would need to be improved also, to keep the overall productivity. Interested in the subject of chunking I remain. ▲ Collapse
Christian Romeo NJIA
Subject:
Comment:
The contents of this post will automatically be included in the ticket generated. Please add any additional comments or explanation (optional)