< Back to portfolio

Product Description

CADChain has taken on the Auto-Summarization Challenge created by the Flemish Radio and Television Organization (the VRT) and will build an auto summarization model for extractive summarizations of media articles. The main goal is to create a system that can automatically summarize news articles without the key phrases and sentences being modified. CADChain’s approach is based on linguistic knowledge and uses existing AI models that can be trained further.

The first step is to use our linguistic knowledge to define what aspects in a sentence can be removed when a short summary is requested and what would be considered ‘additional detail’. This is called our Nearest Neighbor expansion.

The next step is to train AI models to value each derived sentence for importance and to use the importance classification to include more sentences in the summary.

The third step is to wrap this in a user-friendly interface which makes the process understandable for the writers and at the same time allow custom entries or changes to the result of the algorithm. The journalist can adjust more specific parameters for their article’s summarization and directly see the result. Summarization length can be variably defined based on parameters such as article length, requested duration, method of increasing the size of the summary.

Usage of Standards for data interoperability:

The implementation of the web applications and connectors for VRT to embed this in their own systems are built using web-frameworks based on Javascript/Typescript. The media samples are using JSON which is also the format of the standardized responses of our connector to VRT.

CADChain is relying on pre-existing models that understand language such as “OpenAI’s GPT3” (a model that understands the meaning of texts, can answer questions and can be taught what the desired response is), but are also using custom algorithms made using Amazon Sagemaker software for parts that don’t require the intricate detail of the (more expensive) openGPT3 model.

Company Description

CADChain B.V. is a deep-tech startup with a focus on emerging technologies, founded in 2018. It addresses the issue of safe storage and exchange of valuable digital assets, while preserving the IP of the rightful owners. This also covers trade secrets protection in the creator economy, prevents counterfeit products, and facilitates technical developments.

After the validation of the business case by the Dutch Ministry of Economics, CADChain was awarded several grants to do feasibility studies, a research and development project with two other companies and Proof of Concept financing.

The company has since launched a public beta of the blockchain registration solution for product design files created in Autodesk Inventor (software for industrial designers to create 2d/3d models) and is currently working on creating the same solution for the open source 3D editing software package (Blender) and for Fusion360.

The team has startup, corporate, academic, and political experience; stable access to a diverse talent pool and experienced advisors. During the pandemic the team initiated a nonprofit project to bring more women into IT and started researching and developing new concepts involving data analytics and machine learning.