Migrato

Founded in 2014 and headquartered in Strijen in the Netherlands, Migrato helps organizations to analyze, inventory, cleanse and migrate their unstructured content. Using custom-built solutions, the company transforms unstructured data into actionable insights that add value to employees and business processes.

Business problem

Migrato's problem consisted on helping government organizations in the Netherlands comply with new legislation that mandates the proactive publication of public-interest documents, while ensuring the removal of all personal data. While Migrato already specializes in processing unstructured content and has successfully facilitated content migration projects, the company’s existing technology lacked the performance and scalability to handle the large volumes and complexity of document processing required by the new regulations. Specifically, the challenge is to efficiently process hundreds of thousands of documents, accurately extract content, and ensure that no GDPR-sensitive data—such as personal names, bank details, or social security numbers—remains. This task requires a deeper understanding of the content and context of the documents, pushing Migrato to enhance its natural language processing capabilities to meet the increased demand and complexity driven by this legislation.

AI solution

The solution was the IBM Watson Natural Language Processing Library for Embed. This containerized library enabled Migrato to integrate advanced natural language AI into their existing systems. Built on a combination of open-source and IBM Research NLP algorithms, the solution allowed the Company to accurately detect and redact sensitive personal information from unstructured text data, which was essential to comply with the new Open Government Legislation in the Netherlands. The IBM Watson NLP Library provided the tools for more accurate and efficient document processing like advanced topic keyword extraction, improving Migrato's ability to understand the context of documents.

Implementation challenges

Results

Migrato successfully implemented the IBM Watson Natural Language Processing Library, which significantly enhanced their document processing capabilities. The results were impressive: they achieved greater speed and accuracy in detecting and redacting sensitive information from documents, allowing them to comply with the new legislation. The implementation was so efficient that Migrato was able to put the new solution into production within just five days. The solution also enabled more advanced topic keyword extraction, allowing Migrato to better understand the context and meaning of unstructured data.