The aim of the Workshop on Semantic Methods for Events and Stories (SEMMES) was to ofer an opportunity to discuss the challenges related to dealing with events and stories, and how we can use semantic methods to tackle them, also in combination with methods from other fields, including machine learning, narratology or information extraction.
CEUR ceur-ws.org
Representing and instantiating events has always been a crucial task for the Semantic Web
community, with some relevant contributions such as specialised ontologies [
The workshop has been held on May 29th, 2023, opened by the keynote talk “More than one side to every story” of our invited speaker Victor de Boer, Associate Professor (UHD) at the User-Centric Data Science group at the Computer Science department of the Vrije Universiteit Amsterdam (VU) and a co-director of the Cultural AI Lab. The keynote highlighted the importance of polyvocality, i.e. the need to go beyond the common version of the information that we have in our system, embracing diferent points of view and a multiplicity of interpretations [ 5].
The workshop has been followed by the presentation of 5 papers, of which 3 long papers and 2 short papers, organised in two sessions.
He Tan et al. introduced A Semantic Representation of Pedestrian Crossing Behavior, proposing an RDF representation of the latter in order to help systems in predicting future ones. Guillem Anais et al. presented their work for representing and visualising the diferent possible alternatives in the reconstruction of the destroyed parts of Notre-Dame cathedral in Paris, titled Let the fallen voussoirs of Notre-Dame de Paris speak: Scientific Narration and 3D Visualization of Virtual Reconstruction Hypotheses and Reasoning; this work has been awarded with the best paper award of the workshop. The GOLEM Triple Store: A Graph-based Representation of Narrative and Fiction has been presented by Franziska Pannach et al. as a way to represent fanfictions as pieces of cultural heritage in evolution. Cosimo Palma presented a way to compute interestingness with formal metrics proposed in Modelling Interestingness: a Workflow for Surprisal-based Knowledge Mining in Narrative Semantic Networks. Lastly, Myrto Koukouli et al. presented their work on storytelling in the cultural domain called Creating and applying a data model for an Augmented Documentation of Cultural Heritage.
The workshop attracted over 20 attendees in this edition. Details about the workshop, including the Program Committee, are available at https://anr-kflow.github.io/semmes/.
This workshop has been partially supported by the French National Research Agency (ANR) within the kFLOW project (Grant n°ANR-21-CE23-0028), the MUHAI project (Horizon 2020, Grant n°951846) and the Sony Computer Science Laboratories-Paris. [5] M. van Erp, V. de Boer, A Polyvocal and Contextualised Semantic Web, in: The Semantic Web, Springer International Publishing, Cham, 2021, pp. 506–512.