Named Entity Recognition and Classification in Historical Documents: A Survey

After decades of massive digitisation, an unprecedented amount historical documents is available in digital format, along with their machine-readable texts. While this represents a major step forward respect to preservation and accessibility, it also opens up new opportunities terms content mining the next fundamental challenge develop appropriate technologies efficiently search, retrieve explore information from ‘big data past’. Among semantic indexing opportunities, recognition classification named entities are great demand among humanities scholars. Yet, entity (NER) systems heavily challenged diverse, noisy inputs. In survey, we present array challenges posed by NER, inventory existing resources, describe main approaches deployed so far, identify key priorities for future developments.