Over to our AI experts from the apoLAB

What makes our AI experts in the apoLAB tick? What are they researching? What are they interested in? And do they live up to the cliché of being socially awkward loners? Let’s find out in this interview with our in-house developers Raimon and Szymon, who are pouring their expertise and passion into the areas of translation technology and machine learning.

Apostroph AI experts

How did you end up in the world of languages at Apostroph?

Szymon: My career began with me developing chatbots and voice assistants. I’m still fascinated by that technology and I want to keep learning more about it. I can do that right here at Apostroph. Our team is made up of some really cool people. We take a practical approach to solving real-life problems in the language industry. That’s exactly what I want to be doing, so here I am!

Raimon: Apostroph is a tech-savvy company that is focused on the future. The management team understands the importance of IT and gives us the freedom and resources we need to develop and create effective new solutions. I’m happy to have found a job that challenges me and allows me to use my knowledge of machine learning.

Since you mentioned machine learning (ML), can you tell us a bit more about it?

R: Machine learning is a subset of artificial intelligence. Algorithms analyse patterns in datasets that can be used to develop solutions. ML is absolutely key to the work Apostroph is doing with words and languages.

Did you always know you would end up working in IT?

S: I can’t imagine doing anything else. After I had built my first PC at the age of 13, I just knew that I’d end up working in IT. I spent time learning about machine learning when I was studying and I decided to make a career out of it.

R: It was a similar story for me. I was enthusiastic about technology from an early age too.

KI-Spezialisten von Apostroph Group

What do you do? What are you working on at the moment?

S: We find technical solutions. It’s our job to find the most efficient process route that is intuitive and effective for our clients, while ensuring that linguistic quality can be delivered. With all of that in mind, we start by assessing the scope of a project. It’s so important that we understand the business problem fully. We do our research by reading relevant scientific and academic papers and check out the state-of-the-art solutions being suggested by researchers. We check and revise the relevant data resources and create a machine learning solution on the basis of that data.

R: At the moment, I’m experimenting with the idea of adapting a model that works a bit like ChatGPT but on a smaller scale and in a more specific niche.

Like an Apostroph chatbot?

R: Yes, focussing on translation and proofreading, specifically relating to the services we offer here at Apostroph. While more general models like ChatGPT could actually be useful to us in our world of language, they still can’t be relied upon to deliver the accurate linguistic results we need. It's not a case of one model fits all. So we’re working on a custom solution of our own.

How are things looking in terms of data security?

R: This is such an important topic. The data security infrastructure here in Switzerland is forever evolving. We keep on adding to our capacity for internal storage solutions here.

S: We view it as absolutely essential that any data we process and any systems we develop remain right here in Switzerland at all times. We take extreme care to keep all the data we process safe and secure – and that includes data generated using AI.

What’s going on with the likes of machine translation and translation memories?

S: Machine translation is an interesting area to follow at the moment because lots of people are experimenting and some are even trying to bring about a paradigm shift, with large language models (like GPT) being used for automated translation instead of machine translation models that are specifically trained. We are keeping a close eye on these developments and looking into the results and implications of an approach along these lines.

R: One of the biggest problems with multilingual models is that there is conflict between different languages within a model when it comes to parameters. This means that the training data for different languages is out of balance, which can result in poorer results being delivered for less common languages. A new innovation published by Apple is exclusive model parameters that apply to a single language. It just goes to show that there is still plenty of scope for innovation in machine translation. I know that I’m excited to see how good MT can get.

Looking into your crystal balls, what do you think the future holds for IT in the world of languages?

S: I hope that models for text comprehension and generation continue to improve. They are becoming increasingly intelligent and learning to solve complex problems using examples. A single Shakespeare poem will be enough of a prompt for more poems to be written in the style of Shakespeare.

I hope we see more of the new efficient ways of training large language models so that a development process no longer takes a single person 100 years. This will open things up beyond the realms of tech giants.

I also think that our devices are only going to become more powerful, presumably allowing many language models to be run locally rather than just in US-based clouds. It’s possible that we will soon start to see more end-to-end translations, like audio-to-text, audio-to-audio and image-to-text, without complex pipelines consisting of multiple models. We’d be excited to see the rise of simpler, more elegant end-to-end pipelines trained using high-quality data.

R: The role of our linguists will shift towards text managers. They will need to manage a number of technology systems to create linguistic processes. Translations and texts generated by machines will need less and less linguistic input. Linguistic expertise and cultural sensitivity will go hand in hand with an understanding of technology.

KI-Spezialisten von Apostroph Group

People tend to think that anyone working in IT must be a loner who is glued to their computer screen.

S: Yes, I know. But I can confirm that Raimon and I definitely don’t live up to that cliché. The IT work we do at Apostroph requires us to talk to our colleagues so we can find the solution together. We love working with the other teams with the aim of understanding what our clients need and solving their problems. I think it’s brilliant that people place their trust in us and offer us their support. We can use state-of-the-art technology for our research and work on our own professional and personal development as engineers and as people.

R: There’s no way you could call us loners!

Thank you for chatting to us today!

Raimon Wintzer

Language Technology Engineer, Apostroph Switzerland

Raimon Wintzer is a Language Technology Engineer with a Bachelor’s degree in Computer Science and a Master’s degree in Biomedical Computing. Raimon speaks English, German, French and Russian – and is currently learning Chinese. Old Soviet comedies make him laugh out loud. The book on his bedside table right now is Jane Eyre by Charlotte Brontë, which tells the story of an orphan living in Victorian England.

Szymon Ruciński

Junior Language Technology Engineer Apostroph Switzerland

Szymon Rucinski is a Junior Language Technology Engineer with a Master’s in Machine Learning and Software Engineering. He speaks Polish, German, English and... Python (a programming language). When he has finished work for the day, he works on his own computer vision projects for fun. He’s not too bothered about bingeing series on Netflix, but he recently enjoyed watching ‘Quo Vadis’, a 1951 epic film set in ancient Rome. Szymon runs and cycles to keep fit. He’s currently reading ‘Pedalling Poland’ by Bernard Newman. The book describes a cycling adventure in 1934 through his native Poland, a beautifully natural and traditional backdrop.

Would you like to receive regular updates on new customer projects and news about Apostroph?

In our newsletter, we will surprise you with articles that are as informative as they are entertaining. We would be delighted to welcome you to our community of 20,000 newsletter followers.

Achieving goals together

  • Your projects in the best hands

    We work with single points of contact. As a result, you will be looked after by a highly experienced contact person who takes your needs into account and keeps you up to date at all times.
  • We speak your language

    Depending on the project, we put together specific teams of internal and external experts who are well versed in your corporate language.
  • Language intelligence

    Our in-house IT and development department ensures the clever use of technologies so that man and machine are in harmony in an intelligent way.