Research and Innovation (R&I) FUSION Programme - Malta Council for Science and Technology (MCST) as the Managing Authority.
In today’s digital world, book keeping and accounting tasks still involve a huge amount of paperwork and tedious manual interventions that ultimately determine process efficiency and cost, and are a barrier to automation. E-invoicing standards have therefore been developed to reduce manual work. However most companies, especially the smaller ones, still make exclusive use of either paper, email or pdf invoices, receipts and purchase orders, where the semantic information is neither seen nor understood by the machine, limiting further processing and automation.
It is therefore desirable to have systems that extract the semantic information from these documents. In this respect, off-the-shelf commercial products are either characterised by limited functionality, increasing the incidence of human intervention and limiting further tasks, or require the periodic intervention of higher order skills to re-train and maintain a working system.
The Malta Council for Science and Technology (MCST) funded Automated Document Analysis and Classification for Enhanced Enterprise Efficiency (ADACE3) project plans to leverage state of the art artificial intelligence algorithms, namely self-supervised learning, joint vision-language models and never-ending learning techniques, to develop a system that minimises human intervention and is potentially more attractive to the small company market, in terms of cost and ease of use.
The project, which is a joint effort between the University of Malta and PTL Ltd, a leading technology company, plans to develop a minimum viable product that will potentially lead to on the field testing and commercialisation. From a scientific point of view, the project is expected to advance the state-of-the-art in artificial intelligence.