Search

Data are the treasure of digital services as long as data are cleaned, unbiased, as well as combined with explicit and machine processable semantics in order to foster exploitation. Unstructured data like plain text are often self-explicit (all the necessary information to understand the content is in the phrase or its surroundings, with a structure built from known rules), the challenge being to extract the relevant elements and the correct meaning in a given context. On the other hand, structured data like tables have latent meaning that can only be understood by human through implicit mechanism (inference) in the light of their own knowledge, as there is no explicit context. These data being the most common type companies want to leverage on to run AI processing, adding a semantic layer on top of tabular data is a key asset to enhance data exploitation.
DAGOBAH, a research platform resulting from Artificial Intelligence projects, aims at providing an end-to-end, context-free, semantic annotation system for tabular data, resulting in enriched knowledge graphs that users can then leverage on to meet several needs. DAGOBAH is an on-going collaborative research project developed by Orange Labs teams from Belfort and Rennes in association with EURECOM Data Science Department from Sophia Antipolis.