lise stork

Museums, archives and digital libraries make increasing use of Semantic Web technologies to enrich and publish their collection items. The contents of those items, however, are not often enriched in the same way. Extracting named entities within historical manuscripts and disclosing the relationships between them would facilitate cultural heritage research, but it is a labour-intensive and time-consuming process, particularly for handwritten documents.
It requires either automated handwriting recognition techniques, or manual annotation by domain experts before the content can be semantically structured. Different workflows have been proposed to address this problem, involving full-text transcription and named entity extraction, with results ranging from unstructured files to semantically annotated knowledge bases. Here, we detail these workflows and describe the approach we have taken to disclose historical biodiversity data, which enables the direct labelling and semantic annotation of document images in hand-written archives.

Large and important parts of cultural heritage are stored in archives that are difficult to access, even after digitization. Documents and notes are written in hard-to-read historical handwriting and are often interspersed with illustrations. Such collections are weakly structured and largely inaccessible to a wider public and scholars. Traditionally, humanities researchers treat text and images separately. This separation extends to traditional handwriting recognition systems. Many of them use a segmentation free OCR approach which only allows the resolution of homogeneous manuscripts in terms of layout, style and linguistic content. This is in contrast to our infrastructure which aims to resolve heterogeneous handwritten manuscript pages in which different scripts and images are narrowly intertwined. Authors in our use case, a 17,000 page account of exploration of the Indonesian Archipelago between 1820–1850 (“Natuurkundige Commissie voor Nederlands-Indië”) tried to follow a semantic way to record their knowledge and observations, however, this discipline does not exist in the handwriting script. The use of different languages, such as German, Latin, Dutch, Malay, Greek, and French makes interpretation more challenging. Our infrastructure takes the state-of-the-art word retrieval system MONK as starting point. Owing to its visual approach, MONK can handle the diversity of material we encounter in our use case and many other historical collections: text, drawings and images. By combining text and image recognition, we significantly transcend beyond the state-of-the art, and provide meaningful additions to integrated manuscript recognition. This paper describes the infrastructure and presents early results. Full text is available here https://www.springer.com/us/book/9783319758251 and here: https://research.utwente.nl/en/publications/towards-a-digital-infrastructure-for-illustrated-handwritten-arch

Geographical and taxonomical referencing of specimens and documented species observations from within and across natural history collections is vital for ongoing species research. However, much of the historical data such as field books, diaries and specimens, are challenging to work with. They are computationally inaccessable, refer to historical place names and taxonomies, and are written in a variety of languages. In order to address these challenges and elucidate historical species observation data, we developed a workflow to (i) crowd-source semantic annotations from handwritten species observations, (ii) transform them into RDF (Resource Description Framework) and (iii) store and link them in a knowledge base. Instead of full-transcription we directly annotate digital field books scans with key concepts that are based on Darwin Core standards. Our workflow stresses the importance of verbatim annotation. The interpretation of the historical content, such a resolving a historical taxon to a current one, can be done by individual researchers after the content is published as linked open data. Through the storage of annotion provenance, who created the annotation and when, we allow multiple interpretations of the content to exist in parallel, stimulating scientific discourse. The semantic annotation process is supported by a web application, the Semantic Field Book (SFB)-Annotator, driven by an application ontology. The ontology formally describes the content and meta-data required to semantically annotate species observations. It is based on the Darwin Core standard (DwC), Uberon and the Geonames ontology. The provenance of annotations is stored using the Web Annotation Data Model. Adhering to the principles of FAIR (Findable, Accessible, Interoperable & Reusable) and Linked Open Data, the content of the specimen collections can be interpreted homogeneously and aggregated across datasets. This work is part of the Making Sense project: makingsenseproject.org. The project aims to disclose the content of a natural history collection: a 17,000 page account of the exploration of the Indonesian Archipelago between 1820 and 1850 (Natuurkundige Commissie voor Nederlands-Indie) With a knowledge base, researchers are given easy access to the primary sources of natural history collections. For their research, they can aggregate species observations, construct rich queries to browse through the data and add their own interpretations regarding the meaning of the historical content.

Large collections of historical biodiversity expeditions are housed in natural history museums throughout the world. Potentially they can serve as rich sources of data for cultural historical and biodiversity research. However, they exist as only partially catalogued specimen repositories and images of unstructured, non-standardised, hand-written text and drawings. Although many archival collections have been digitised, disclosing their content is challenging. They refer to historical place names and outdated taxonomic classifications and are written in multiple languages. Efforts to transcribe the hand-written text can make the content accessible, but semantically describing and interlinking the content would further facilitate research. We propose a semantic model that serves to structure the named entities in natural history archival collections. In addition, we present an approach for the semantic annotation of these collections whilst documenting their provenance. This approach serves as an initial step for an adaptive learning approach for semi-automated extraction of named entities from natural history archival collections. The applicability of the semantic model and the annotation approach is demonstrated using image scans from a collection of 8, 000 field book pages gathered by the Committee for Natural History of the Netherlands Indies between 1820 and 1850, and evaluated together with domain experts from the field of natural and cultural history.

Available for free until January 23, 2020! Click here: https://authors.elsevier.com/c/1aAWX5bAYUWYbx