Building Semantic Metadata for Historical Archives through an Ontology-driven User Interface

Abstract

Historical archives represent an immense wealth, the potential of which is endangered by the lack of effective management and access tools. We believe that this issue can be faced by providing archive catalogs with a semantic layer, containing rich semantic metadata, representing the content of documents in a full-fledged formal machine-readable format. In this paper we present the contribution offered in this direction by the PRiSMHA project, in which the conceptual vocabulary of the semantic layer is represented by computational ontologies. However, acquiring semantic knowledge represents a well-known bottleneck for knowledge-based systems: in order to solve this problem, PRiSMHA relies on a crowdsourcing collaborative model, i.e., an online community of users who collaborate in building semantic representations of the content of archival documents. In this perspective, this paper aims at answering the following research question: Starting from the axioms characterizing concepts in the computational ontology underlying the system, how can we derive a user interface enabling users to formally represent the content of archival documents by exploiting the conceptual vocabulary provided by the ontology? Our solution includes the following steps: (a) A manually defined configuration, acting as a pre-filter, to hide "unsuited" classes, properties, and relations; (b) An algorithm, combining heuristics and reasoning, which extracts from the ontology all and only the "compatible" properties and relations, given an entity (event) type. (c) A set of strategies to rank, group, and present the entity (event) properties and relations, based on the results of a study with users. This integrated solution enabled us to design an ontology-driven user interface enabling users to characterize entities, and in particular (historical) events, on the basis of the vocabulary provided by the ontology.

Wikidata Support in the Creation of Rich Semantic Metadata for Historical Archives

“…In order to add annotations to a selected document, users can click View or add annotations (Figure 2): the system pops up a window (Figure 3) where the user can select an existing entity or add a new one by clicking on Add (and link) new entity. In the latter case, after having selected the suited entity type (e.g., Azienda-Company) and having provided a label (e.g., "FIAT"), the user has to fill in a form (see Figure 4) in which all properties characterizing the entity are listed (actually, properties are organized in three tabs, containing important, useful, and other properties, respectively; see [4]). For all the listed properties but the first one, the user is invited to search the KB to select an existing entity (e.g., Torino for the ubicata in-located in property); if no suitable entity is found, the user has the possibility to create a basic entity, i.e., an entity characterized only by type and label.…”

“…As described in Section 2, she can click View or add annotations (Figure 2) to get the window enabling her to add a new entity (by clicking Add (and link) new entity: Figure 3). The user can now select the entity type, PhysicalPerson in our example, and provide a label, e.g., "Sandro Pertini": This makes the system generate the form to be filled in to characterize the new entity (Figure 4); the form containing properties suitable to describe the new entity is dynamically generated on the basis of the selected type (class) for the entity itself (see [4]). At this point, the user can ask for suggestions from external resources (Wikidata in the current prototype) by clicking Search on external resource.…”

“…Secondly, the different approaches by which HERO and Wikidata were built entail some significant ontological differences between the two semantic models. HERO is based on an accurate ontological analysis, which exploits both existing foundational and core ontologies and the domain experts' knowledge, which was aimed at providing a well-founded and sound framework for domain-specific instance data [4,42]. Differently, Wikidata [7] is a large-scale crowd-based project aimed at collecting and providing users with a free huge amount of data in any domain.…”

“…The main goal of PRiSMHA is the design and implementation of an ontology-driven prototype platform supporting users in semantic metadata production. The assumption behind the approach adopted in the project, shared within the Digital Humanities community (see, for instance, [3][4][5]), is that an effective and engaging access to historical archives needs a rich semantic knowledge, based on a domain ontology, describing the content of archival documents.…”

“…When the user is filling in the form to characterize a new entity to be added to the Semantic KB, an algorithm (described in [4]) singles out the suitable properties for that entity, as well as the valid classes for their fillers.…”