Work projects

Conferences and events in the medical sector often involve numerous speakers, presentations and scientific works. In this challenge, presented by a real client, we used Natural Language Processing to make sense of the sizable amount of material that is the output of such conferences by drawing the most relevant insights for both participants and sponsors.

I designed and developed the ML component of a system to identify the structure (chapters, paragraphs…) from an insurance document in PDF format. The extracted text and structure are saved in XML format.

As part of a search engine for institutional documents, I designed and developed a fast pipeline for the interpretation and expansion of the user query. In the query, named entities, dates, domain terms and complex terms are detected.

I designed and developed a machine learning system, capable of surfing the web and recognizing the URL of an institutional data source. If the page is part of the known types, the system chooses the most suitable crawler for scraping this page.

I participated in an experimentation commissioned by Anas, aimed at developing a low-cost IOT+ML system for predictive maintenance of road infrastructure. Working with sensor data, I trained various neural networks in order to learn the “behavior” of the monitored infrastructure and report significant future deviations.