Skip to main content
Loading...

Aymen Merchaoui wrote his master’s thesis in Artificial Intelligence at the University of Santiago de Compostela in collaboration with Altia.

With the advancement of Artificial Intelligence technologies, companies need more professionals trained in this field. This is the case of Aymen, who not only completed the master’s degree in Artificial Intelligence at the University of Santiago de Compostela, but also achieved a score of nine out of ten in his master’s thesis, a project conducted in collaboration with Altia, where he now works as an Artificial Intelligence Engineer.

In his thesis called "Developing an OCR+NER solution to extract information from invoices", Aymen designed and developed a system that uses computer vision and natural language processing (NLP) techniques to extract text from invoices and detect important information such as supplier names, dates, and other relevant data.

Aymen Merchaoui

Aymen Merchaoui - Artificial Intelligence Engineer

What was the role of Artificial Intelligence in this project?

"The AI-related aspects I dealt with most in the project were computer vision, natural language processing (NLP), and multimodal named entity recognition (NER) models. I also used OCR (Optical Character Recognition) techniques to extract text from invoice images and NER methodologies."

"A key component of my work was the use of LoyoutIM, a multimodal model that combines textual and positional information to predict labels. This model is characterised by its ability to understand not only the content of the text, but also the spatial arrangement of the elements in the invoice, which is crucial for accurately capturing the structure and context of the information."

How was the experience of developing this project with us?

"My experience of working with Altia has been excellent. From the beginning, I received extensive support from the Altia team, who provided me with the tools I needed to do my job. I would especially like to thank Pablo Méndez for his guidance and leadership throughout the project. His expertise was crucial to the success of the work. I would also like to thank my colleague Nerea for her constant cooperation. Working together was a very valuable experience that greatly improved the final results.”

What aspects of working with a company like Altia would you highlight?

"It was a very useful experience in several important aspects: I had the opportunity to be in a real business environment, which helped me to understand how Artificial Intelligence technologies are used in everyday work. In addition, I was able to not only think about technical solutions, but also implement them in real projects. This gave me a broader perspective on practical challenges and best practices in artificial intelligence.”

How do you hope your training in AI will contribute to your professional development?

"I hope that my training will enable me to apply innovative solutions to complex problems in the professional field and to use my skills to improve processes, optimise business decisions and develop advanced technological products. I also hope to be prepared to face new challenges in the field of AI and to contribute to Altia's growth."

At Altia, we actively collaborate with educational institutions to contribute to the training of future professionals. A collaboration that we believe to be necessary and mutually beneficial. In this case, the collaboration with a master’s degree focused on AI, a field with great potential for expansion, is crucial. Pablo Méndez, Director of Artificial Intelligence at Altia, emphasises that in addition to the satisfaction of helping students acquire a more practical vision of AI than the academic one - with a product focus - it is a great opportunity to attract talent from our universities to join our teams.

"Work placements with businesses involve a change in approach, transitioning from academic problems based on theory to developing solutions for actual client challenges. Students find out how these solutions are developed in a company by joining our AI development teams. Creating real solutions is not just about an algorithm trained on a notebook; it is about a product that can be deployed as an API in production, prepared to scale, that must pass quality and load tests, etc." explains Pablo.