Descripció del projecte
Historical documents reflect the identities and contexts of the past, and the access to their contents allows citizens at large to know their individual and collective memory. Search centered at people is very important in historical research, including family history and genealogical research. Genealogical documents such as birth, marriage or dead certificates or census records contain information that reflect a picture of a historical context: a person’s life, an event, a location at some period of time. The CVC and Qidenus are currently working in the development of computational methods for the massive analysis of digitized historical demographic documents.
In order to extract the information contained in demographic manuscript documents, it is necessary to investigate on semantic annotation techniques to associate a semantic meaning to the words of the document. In particular, it is necessary the detection of the so-called named entities and their associated semantic category (concept) such as a person’s name, last name, place, date, occupation, etc. Thus, the information contained in the documents can be extracted labeled and stored in databases, and hence making the information accessible and searchable.
Methodologically, the thesis will focus on techniques that learn a joint embedding space that associates visual features extracted from images to concepts. We plan to use deep neural networks to associate semantic categories to named entities.
