Generating an inter-linguistic map of action concepts through multiple clustering on the IMAGACT ontology

This study investigates the automatic identification of action concepts using machine learning algorithms applied to a linguistic dataset derived from the IMAGACT ontology of actions. This resource comprises 1,010 action concepts, each represented by video scenes and enriched with multilingual linguistic annotations. Specifically, each video scene is associated with the complete set of verbs that can be used to describe the depict-ed action in each of the languages included in the ontology. Based on these data, auto-matic clustering of video scenes was conducted using the associated lexical items as fea-tures, under the hypothesis that semantically similar actions tend to be expressed by simi-lar groups of verbs. Hierarchical agglomerative clustering was first employed to establish an evaluation framework and to construct a gold standard of validated action clusters. Subsequently, a semi-supervised approach based on Affinity Propagation was trained on the annotated data. Cluster coherence was evaluated, yielding promising results in terms of internal consistency and semantic interpretability. In addition, an interactive web inter-face of the action map was developed to enable users to visualize and browse the result-ing clusters of video scenes.