May the FORCE be with Semantics: exploiting LLMs to Image Schematic Knowledge Enrichment

This paper addresses the underspecification of the FORCE image schema. We present a novel hybrid pipeline that combines large language model interactions, linguistic analysis, and knowledge extraction techniques to expand upon Johnson’s initial categorization of FORCE types. Our methodology employs Claude 3.5 Sonnet for domain exploration, generates a dataset of 100 force-expressing verbs with contextual sentences, and integrates findings into ImageSchemaNet through AMR2FRED processing and SPARQL querying. Key contributions include: (1) a more nuanced understanding of the FORCE image schema, (2) a validated dataset of force-related linguistic expressions, and (3) an enhanced ontology with empirically derived FORCE concepts. This work bridges the gap between abstract image schema theory and specific linguistic realizations of FORCE, offering practical tools for natural language processing, knowledge representation, and cognitive computing.