NLP: Natural Language Processing
The large amount of information collected every day by archaeologists during the excavation campaigns, published through journals, books and catalogues, is not easily accessible. It requires spending a lot of time, often with unsatisfactory results, in the search for specific documents and information within larger texts. The idea of this project comes from the need to simplify and make more immediate access to data through a semi-automatic procedure allowing for the extraction of information from archaeological texts, in a sector where the exponential increase of digital documentation raises important questions about the management, use and added value of the data.
The techniques allowing the extraction of such information from documents are part of Natural Language Processing (NLP): these are algorithms that extract, structure and analyze information from textual sources. The goal is extremely ambitious, but this does not mean replacing human work with computer work, but rather supporting it, making it easier and strengthening it.