Author - Gábor Bessenyei

Data Center Maintenance

Update: all Globalese systems are up and running. Thank you for your patience! IMPORTANT: on 26th July 2019, between 17:00 and 24:00 CEST, the Globalese systems will not be available due to planned Data Center Maintenance. Any updates will be posted in this news.

Meet Globalese at GALA Munich!

The Globalese team led by CEO Gábor Bessenyei is looking forward to meeting you at the GALA's annual Language of Business conference in sunny Munich.

Photography by Anrie - Created and uploaded by Anrie., CC BY-SA 3.0, https://commons.wikimedia.org/w/index.php?curid=4075361 Do you have questions to us about Neural Machine Translation? Wondering about expected ROI after a NMT rollout? Are you worried about the right terminology in the MT process? Would you like to know more about AIDA, Globalese's automated in-domain adaptation technology? Do you simply need a coffee and a couple of friendly faces? Sign up for a meeting with us and we will be looking forward to seeing you at our booth!

Breaking the terminology barrier in Neural Machine Translation

[lead]One challenge Neural Machine Translation technology faces today stems from the very same thing which makes it so amazing and effective. Let's see how Globalese solves the Terminology Problem with the help of AIDA.[/lead]  
The end of the second act of the opera Aida in the Verona Arena in July 2011. – AIDA, Automated In-Domain Adaptation is probably not as grandiose, but probably similarly spectacular for terminology-savvy users of Neural Machine Translation. Photo by Jakub Hałun, CC BY-SA 4.0
The end of the second act of the opera Aida in the Verona Arena in July 2011. – AIDA, Automated In-Domain Adaptation is probably not as grandiose, but probably similarly spectacular for terminology-savvy users of Neural Machine Translation. Photo by Jakub Hałun, CC BY-SA 4.0

Neural Machine Translation was an amazing break-through from many points of view. It has improved the overall quality of machine translations compared to pre-neural times. It has provided, for the first time, truly usable and sound quality output for the language industry.  It has also opened up opportunities for languages like Japanese, Chinese or Russian, which otherwise performed poorly on Statistical MT technology.

The downside of the Neural Machine Translation revolution: terminology

As with every groundbreaking invention, NMT technology also had its limitations. One of the major issues with Neural was handling terminology. This major challenge stems from the very reason of what makes NMT so truly exciting. Unlike with statistical MT technology, where it was possible for users to provide a terminology list, which the MT system could safely rely on during translation, it was not directly possible to provide a master terminology for the translation process in the NMT world. Technically, you can, of course, introduce a glossary to an engine as part of the training corpora, but this will not act the way you would expect. It will not prioritize the translations in the glossary over the content in the rest of the training data. In the NMT technology, there is currently no way to influence the terminology translation directly during the machine translation process.

Are you a content owner or an LSP? Give Globalese a go now and grow your business with the power of Neural MT! Click here and start your free trial now!

That doesn’t mean that developers hasn’t made attempts to solve this issue. One of the solutions we have seen from many MT providers is to implement terminology replacement based on a glossary after the machine translation phase. While it certainly sounds promising, unfortunately the results are not always that encouraging. The problem is that you are running a considerable risk of losing grammatical information during the replacement process. Just imagine the problems a changed gender of a word can cause in German. In better cases, you will have to spend many hours of editing to fish out the problematic bits. In some cases, you end up with a limited usability output that leaves you, your clients and your translators disappointed.

Introducing automated in-domain adaptation (AIDA)

Globalese is answering to this challenge by introducing its proprietary technology, the automated in-domain adaptation. This technology will provide you with a yet unparalleled improvement. So what is this all about? By using the automated in-domain adaptation technology, as a Globalese user, you will have the chance to mark content from the training data of an engine as the most important in-domain content. For example, if a user has a Translation Memory (TM) of a medical device documentation, it can be marked as the master TM. Globalese will analyze the content of the master TM(s) and extend the engine only with similar and related training data from the auxiliary TMs. Additionally, the engine will be tuned based on the master TM. The result is a highly customized engine focusing on the content of the master TM.

Maxing out terminological accuracy and keeping quality

The result of this process will be an engine where the wording and the style of the master TM will get higher priority over the rest of the training data, even if there are concurring terms. This way, you can reach a maximum level of terminology accuracy without having to face the problem of losing grammatical information or decreasing the overall language quality. Naturally, the cleaner and the more up-to-date your master TM is in the relevant topic or domain, the better the overall quality will be. This innovative Globalese solution concerning the terminology barrier of Neural MT technology paves the way to even better optimized workflows. This means that content owners and Language Service Providers can save considerable time and resources in post-editing output.

Join us for a coffee in Munich!

Report on custom NMT from Intento

Intento have released a very interesting report comparing different providers of custom Neural MT solutions. We are proud to see Globalese doing well based on automated evaluation metrics. The position Globalese achieved in human evaluation is mainly determined by the relatively higher number of inaccuracies with numbers and figures, which we have worked on to improve in version 3.5. Considering the fact that one of Globalese's strengths is handling tags, we believe that Globalese, as a 100% neural, 100% custom system, gives a real competitive advantage to our users.

Globalese 3.4 released

In the past months, we have been working hard on improving the two core processes in Globalese: training and translation. Globalese 3.4 brings overall improvements in both departments. Training an engine is now 20% to 60% faster. Translation is 20% to 40% faster overall, and we conducted extensive tests to ensure that automated metrics show at least as good a score as before retraining an engine (as always, this depends on the language combination). Since this a significant change, you will notice that certain engines will be marked for retraining. This makes use of the engine health feature introduced in Globalese 3.3. Note that while you can continue using your engines as they are, retraining them will give you the advantage of faster translation and higher quality. Bugfixes:
  • SDLXLIFF parsing errors for rare segment statuses.
  • Pulling MXLIFF files from a connected Memsource server failed in certain cases.
  • Various tokenisation-related issues in training and translation.