Author Archives: Katrin Affolter

From back pain to computer issues

Fun with Language Working with natural language can be challenging and frustrating, but it can be a lot of fun too. Let me share my newest “fun with language” moment: Research is often done in English, and there are many … Read More

Every cloud has a silver lining

Some months ago, Switzerland went into “lockdown”. This meant that everyone who could work from home should do so. At Balzano Informatik AG, we did that too. It was not always easy, but we adapted, we improved, we made it … Read More

Spine, the newest back stabber

Something aggravating is often referred to as a “pain in the neck.” Well, in my work, perhaps the expression should be “pain in the spine.” In previous posts, I talked a lot about German-specific issues. Today, I want to show … Read More

“A small change for a word, but a big change for the lemmatizer”

In my previous blogs, I talked about the difficulty provided by natural language (e.g. ambiguity and variety) and the medical domain (e.g. medical words unknown in common tools). Today, I want to show you another aspect: How big the impact … Read More

Can you shorten everything?

Remember my blog post about how in German you can string words together to form new ones? As mentioned in that post, this increases the possible terms for pathologies and can be frustrating when trying to find all possible variations of … Read More

Can you hear me?

In the last few weeks, how often have you asked, “Can you hear me?”  I feel like it is the sentence spoken most often while working from home. It is funny how many meetings now start with this question instead … Read More

Working Without Missing a Beat

Software engineers and data scientists are known for working from the basement, in the dark, without sunlight or social interaction – basically socially awkward vampires to the rest of the world. Perfect conditions for working from home. As with any … Read More

«Same Difference»

When humans are talking or writing, they are not as precise as you would think. Usually, this is no issue because the meaning is implied by the context and if not, the other participants will enquire to achieve understanding. Problem … Read More

Can you come up with another one?

Did you ever wonder why computational linguists always say “natural language is ambiguous and various,” as though that is an explanation why their tasks are complicated? I mean, I get it: There are many different languages and they have different … Read More

“The more the merrier!”

This idiom describes pretty accurately how we data scientists feel about the data for our machine learning tasks. Generally speaking, the more data we have during training to put through the machine learning models, the better they get. For our … Read More