We are a team of dedicated software engineers and machine learning experts with a mission to transform documents to value.
A plethora of information is held in tables, the extraction of said data is, however, extremely difficult. turicode has invested in researching the tasks and beats the current state-of-the-art systems.
An important part of training is the evaluation. To help you with the evaluation of your machine learning system, we will present you three useful measures to evaluate the performance of your system.
Our co-founder Martin Keller just returned from a business trip to Hong Kong. Read about his insights into the fintech world of the Greater Bay Area in his article on Medium.
We listed three important points to keep in mind if you want to put together a training set which will make your machine learning system perform at its best.
In August, we attended the Swiss IT fair topsoft and conducted a little survey on the digitization of documents. Read about our findings in our latest article.
After the launch of our technology MINT.extract as a standard product, we asked Aaron Richiger, our machine learning expert and research lead, a few questions about the use of machine learning in MINT.extract. Read his answers here.
Our customers regularly voice questions about the security of their data as it is often their most important asset. turicode is aware of this and therefore processes sensitive customer data based on the highest security standards. This article explains how we deal with data security.
The fourth and last article in our series “Documents to Value” is now online. We have outlined our best practices in integrating a machine learning project into an existing IT architecture.
The third article in our series “Documents to Value” is now published. Learn more about how users can easily label their documents and train specific model.
The second article in our series “Documents to Value” is now published. Learn more about how we use Machine Learning to gain information from documents.
turicode digitizes purchase orders for Wärtsilä, which must be processed daily as PDFs or scans. We present this project together with Wärtsilä at the CognitiveTank organized by SwissCognitive. We are excited to present an example of how MINT.extract in combination with learning systems creates new possibilities in digitalization.
Our AI-based document analysis tool MINT.extract becomes smarter every day, allowing us to understand unstructured data in PDF documents by emulating the mind of a human reader. That is why Swisscom, a leading telecoms company in Switzerland, put us on the Swiss Artificial Intelligence Startup Map.
We proudly presented a feature of MINT.extract that uses deep learning to divide pages into regions according to their content type at SwissText 2018 in Winterthur on 12.-13. June 2018. Are you interested in the technological background? Have a look at our poster!
It's time to unlock the full potential of your documents!
Read our article entitled "Documents to Value"!