Neural Machine Translation is gradually bridging the gap between human and machine translation. Despite the excitement around NMT, the technology isn’t perfect yet. The academic world and the large tech companies are in a race to improve the accuracy and output quality of NMT.
Computers need numbers to make calculations. This means neural machine translation (NMT) needs numbers instead of words. But how do you turn words into numbers?
There’s a lot of talk about Neural Machine Translation (NMT) these days. But few people actually have an idea of how this technology works. No wonder, because there is a lot of mystery around NMT, and explaining it requires some abstract thinking.
In our next three blog posts, we’ll have a closer look under the hood of NMT.
Yamagata Europe has been using machine translation technology since 2009. In this post, we want to give you a short overview of the most frequently used machine translation technologies today: Rule-Based Machine Translation (RBMT), Statistical Machine Translation (SMT) and Neural Machine Translation (NMT).
In today’s globalized economy, more and more Asian companies are spreading their wings across the globe. At rapid pace, these companies are moving away from centralized Asia-based engineering sites towards a distributed model with regional branches. And although geographical boundaries seem to be fading away, there is still one important barrier that needs to be overcome: language. In order to improve corporate communication between different geographical business units, many of Yamagata’s customers are now turning to machine translation.
With business becoming more and more globalized many Asian companies have moved away from centralized engineering sites based in Asia towards split engineering sites across the globe. In order to improve communication between these units several of Yamagata's customers have welcomed the implementation of machine translation.
We’ve completely redesigned our machine translation portal Y-MTS. Y-MTS enables you to translate data in a safe, fast and cost-efficient way.
Not a day goes by on the internet without someone bashing Google Translate for a stupid translation mistake. Memes abound and yes they are funny, at times. Articles on Google Translate fails are shared, liked and reblogged by freelance translators and LSPs alike. But is this helping the translation industry? I don’t think so.
Post-editing is a very broad concept: different post-editing levels can be defined depending on the scope of the project and the customer’s needs. Light post-editing and full post-editing are the most frequently used and applied levels of post-editing.
With so many SMT solutions built around Moses on the market, why would an LSP even bother try building its own? Calculating the ROI when using SMT is difficult enough, let alone the ROI of building your own system. Especially for small LSPs this might seem too large of an investment to be worth considering. So why are we still thinking about it?
The YMTS translation web service provides machine translation to Yamagata Europe clients. This allows clients to use machine translations in their own applications without sending their private data to public providers such as Google. In this blog I will demonstrate how easy it is to use the web service when building applications.
One of the most frequently asked questions surrounding the implementation of Machine Translation is "How do you measure the quality of your MT output?"
- GitHub: the ideal version control and collaboration platform Posted by lee on 21 october
- The Finnish-Japanese connection Posted by jenkins lee on 11 october
- GitHub: the ideal version control and collaboration platform Posted by Steve Mendez Steve on 4 october