The paper presents the Story Map Building and Visualizing Tool (SMBVT) that allows users to create story maps within a collaborative environment and a usable Web interface. It is entirely open-source and published as a free-to-use solution. It uses Semantic Web technologies in the back-end system to represent stories through a reference ontology for representing narratives. It builds up a user-shared semantic knowledge base that automatically interconnects all stories and seamlessly enables collaborative story building. Finally, it operates within an Open-Science oriented e-Infrastructure, which enables data and information sharing within communities of narrators, and adds multi-tenancy, multi-user, security, and access-control facilities. SMBVT represents narratives as a network of spatiotemporal events related by semantic relations and standardizes the event descriptions by assigning internationalized resource identifiers (IRIs) to the event components, i.e., the entities that take part in the event (e.g., persons, objects, places, concepts). The tool automatically saves the collected knowledge as a Web Ontology Language (OWL) graph and openly publishes it as Linked Open Data. This feature allows connecting the story events to other knowledge bases. To evaluate and demonstrate our tool, we used it to describe the Apuan Alps territory in Tuscany (Italy). Based on a user-test evaluation, we assessed the tool’s effectiveness at building story maps and the ability of the produced story to describe the territory beyond the map.
Using knowledge graph embedding models (KGEMs) is a popular approach for predicting links in knowledge graphs (KGs). Traditionally, the performance of KGEMs for link prediction is assessed using rank-based metrics, which evaluate their ability to give high scores to ground-truth entities. However, the literature claims that the KGEM evaluation procedure would benefit from adding supplementary dimensions to assess. That is why, in this paper, we extend our previously introduced metric Sem@K that measures the capability of models to predict valid entities w.r.t. domain and range constraints. In particular, we consider a broad range of KGs and take their respective characteristics into account to propose different versions of Sem@K. We also perform an extensive study to qualify the abilities of KGEMs as measured by our metric. Our experiments show that Sem@K provides a new perspective on KGEM quality. Its joint analysis with rank-based metrics offers different conclusions on the predictive power of models. Regarding Sem@K, some KGEMs are inherently better than others, but this semantic superiority is not indicative of their performance w.r.t. rank-based metrics. In this work, we generalize conclusions about the relative performance of KGEMs w.r.t. rank-based and semantic-oriented metrics at the level of families of models. The joint analysis of the aforementioned metrics gives more insight into the peculiarities of each model. This work paves the way for a more comprehensive evaluation of KGEM adequacy for specific downstream tasks.
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：