Natural history collections provide invaluable sources for researchers with different disciplinary backgrounds, aspiring to study the geographical distribution of flora and fauna across the globe as well as other evolutionary processes. They are of paramount importance for mapping out long-term changes: from culture, to ecology, to how natural history is practiced.This thesis describes computational methods for knowledge extraction from archives of natural history collections---here referring to handwritten manuscripts and hand-drawn illustrations. As we are dealing with heterogeneous real-world data, the task becomes exceptionally challenging. Small samples and a long-tailed distribution, sometimes with very fine-grained distinctions between classes, hamper model learning. Prior knowledge is therefore needed to bootstrap the learning process. Moreover, archival content can be difficult to interpret and integrate, and should therefore be formally described for data integration within and across collections. By serving extracted knowledge to the Semantic Web, collections are made amenable for research and integration with other biodiversity resources on the Web.