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, ofering practical tools for natural language processing, knowledge representation, and cognitive computing.
Image schemas, as fundamental cognitive constr1u]c,thsa[ve been instrumental in our understanding of embodied cognition and conceptual metaphor theory. However, while certain image schemas have been extensively investigated, others remain ambiguous, and a comprehensive, agreed-upon list of these schemas continues to elude researchers. This lack of consensus poses significant challenges for advancing the field and applying image schema theory across various domains, including knowledge representation, natural language processing, and cognitive robotics.
Large Language Models (LLMs) ofer a promising avenue to address some of these challenges. As the most extensive repositories of general approximate commonsense knowledge currently available, LLMs have inadvertently internalized a degree of embodiment “by proxy” through the way language is used to describe the worl2d].[This linguistic representation is inherently grounded in embodied cognition, reflecting how humans conceptualize and interact with their environment. Consequently, LLMs possess a substantial amount of knowledge that is implicitly grounded in their training data, potentially ofering insights into image schemas that have yet to be fully explored or defined.
In the realm of image schemaFso, rce remains notably underspecified compared to more thoroughly
explored schemas such aSsource_Path_Goal and its related families, as highlighte3d].byW[hile
Johnson [
CEUR
ceur-ws.org
This approach not only addresses the scarcity of annotated resources and comprehensive datasets in the domain of image schemas but also opens up new possibilities for understanding how humans conceptualize their experiences. By tapping into the implicit knowledge encoded in LLMs, we can potentially bridge the gap between abstract image schema concepts and their concrete manifestations in language and thought.
The paper is organised as follows: Sect2iopnrovides useful references to IS literarture and in particular aboFuotrce analysis; Sectio3ndetails the hybrid approach; Sect4ioshnows our results and discuss them; finally Section5 envisions future works and concludes the paper.
The dataset, knowledge base, scripts, and full prompts will be made fully available at “camera ready” time.
The concept of image schemas (IS), introduced by Lakof and Johnso1,n4[
Furthermore, IS constitute a finite set of relational primitives that define the uses and afordances of objects within their environments. Prominent examples inCcolnutdaeinment, which represents the capacity of one object to be enclosed within anothSeoru,racned_Path_Goal, which describes the potential or actual movement of objects along specific trajectories. These schemas are not merely static representations but serve as dynamic cognitive structures that underpin more complex reasoning processes.
Indeed, image schemas are widely recognized as foundational elements in human rea1s2o]nainngd [ have been demonstrated to evolve into sophisticated cognitive functions, including natural language processing and the conceptualization of abstract e1n,t1i3t]i.esTh[is evolution occurs through the grounding of these schemas in experiential patterns, highlighting the embodied nature of cognition.
Moreover, image schemas exhibit a remarkable capacity for combinatorial complexity. Consider the
concept of “transportation,” which can be abstracted beyond specific objects to represent the “movement
of object(s) from A to B.” In image-schematic terms, this can be formally described as a combination of
Source_Path_Goal with eitheSrupport orContainment [
Recent advancements in image schema research have investigated the capabilities of this combinatorial
capacity, leading to the development of sophisticated analytical tools and frameworks. Notable among
these are the Image Schema LogISicL [
While corpus-based studie2s2[, 23] and machine learning approach2e4s,[25, 26] have made significant strides in identifying image schemas in natural language, the challenge of comprehensive image schema coverage remains an active area of research.
On the other side, the unique position of LLMs as both products and reflectors of human language use makes them valuable tools for investigating image schemas. By analyzing the patterns and structures within LLM outputs, researchers may uncover new image schemas, clarify ambiguous ones, and potentially work towards a more comprehensive list. Moreover, LLMs could be leveraged to generate synthetic data that captures the nuances of image schemas in linguistic expressions, rapidly expanding the available resources for studying these cognitive patterns.
Retrieval Augmented Generation (RA2G7)] [is a cross-disciplinary research topic which focuses on
refining models to make them able to retrieve precise information from big compressed amount of
(usually textual) data, traditionally in the form of vector embeddings. Recent advancements in knowledge
extraction have made graph generation from text a relatively straightforward process. The recent
emergence of Graph-RAG2[
However, the true challenge lies in aligning this extracted information with existing knowledge structures, such as ontologies or conceptual schemas in knowledge bases, and efectively leveraging existing semantic web resources. To address this challenge, our methodology, shown in Figure1, builds upon previous work, including ImageSchemaNet20[], and enriches the formalized knowledge through two primary approaches. First, we employ a chain of thoughts prompting technique for knowledge elicitation from large language models (LLMs), as detailed in subsequent sections. This process allows us to tap into the vast knowledge encoded in LLMs while maintaining a structured approach to information extraction.
Our methodology also yields a valuable by-product:
synthetic data augmentation for the Image Schema (IS)
Catalogue2[
This section details our experimental approach to exploring and formalFizoirncgetihmeage schema, combining LLM interactions, linguistic analysis, and knowledge extraction techniques. Our methodology encompasses initial domain exploration, focused data generation, and the integration of derived knowledge into existing semantic web resources.
For the generative task it has been used a state of the art model: Claude 3.5 Sonnet, a large language model known for its comprehensive knowledge base and nuanced ability in describing even complex concepts. The whole generation process is freely replicable since it is done via open chat interface. Our experimental approach commenced with a broad domain exploration, centered around the fundamental question: “List which kind of forces can activaFtoertcheeimage schema.”
List which kind of forces can activate the FORCE image schema.
The model provided a detailed list of genFeorrice types, which included: physical forces, psychological forces, social forces, emotional forces, gravitational forces, electromagnetic forces, nuclear forc (strong and weak), frictional forces, tensile and compressive forces, and centripetal and centrifugal forces. This initial output served as a foundation for our subsequent investigation, ofering a diverse range of force categories that could potentially actFiovracteeitmhaege schema.
Building upon this initial output, we employed a chain-of-thought prompting technique to generate a controlled vocabulary for each of Ftohrecsee types. This method involved asking the model to elaborate on each force category, providing examples and related concepts.
Now for each of these points generate a list of terms which can be used as controled
vocabulary to generate a knowledge base.
After careful analysis of the results, we made a strategic decision to focus specifically on physical
forces for several compelling reasons. Firstly, we observed that some of the other categories, such as
psychological and social forces, often represented metaphorical extensions of physical forces. These
metaphorical uses, while interesting, were already grounded in image-schematic concepts and would
potentially introduce complexity in distinguishing between literal and figurative applFicoartcieo.ns of
Additionally, certain categories, such as emotional forces, were deemed too generic and abstract for
our purposes. Moreover, these emotional aspects had been previously addressed in existing literature,
notably in3[
Our next step involved a more focused prompt aimed at extracting a “complete list of verbs expressing Forces.” We instructed the model to concentrate solely on physical forces and provide a comprehensive list of verbs that evoke aFonryce idea.
Ok, now focus only on physical forces and provide a list of all verbs which evokes any
FORCE idea.
The prompt was carefully crafted to elicit a wide range of verbs while maintaining relevance to physical manifestationsFoofrce. This process resulted in a collection of 100 verbs expressing various types ofForces, ranging from common actions like “push” and “pull” to more specific verbs like “torque” and “propel.” To contextualize these verbs and ensure their applicability, we then requested linguistic examples that demonstrate specific occurrenceFsoorfce for each item on the list.
Now provide a sentence as example for each item it this list, which realizes a
situation of FORCE.
The prompt for this stage was designed to generate diverse, realistic sentences that clearly illustrated theForce concept embodied by each verb.
This iterative prompting process yielded a final output of 100 lines, each containing a lexical unit pointing to a type oFforce, accompanied by a sentence illustrating its realization in context. For instance, one entry might include the verb “compress” along with the example sentence “The hydraulic press compressed the metal sheet into a thin disc.” This comprehensive collection serves as a valuable resource for further analysis and applicationFoofrctehe(and possibly other co-occurring) image Lexical Trigger Example Sentence
trapped inside.
resistance.
of people. schema(s) in the field. To ensure the quality and relevance of our dataset, each entry was reviewed by domain experts with previous background in image schemas. The experts evaluated the entries based on criteria such as claritFyoorfce representation, diversityForfce types, and linguistic naturalness of the example sentences. Any disagreements were resolved through discussion, and entries that did not meet the quality standards were replaced or refined through additional prompting sessions with the language model. This results in a synthetic dataset, manually curated, listing 100 verbs expressing Force.
Table?? presents an excerpt from this curated dataset, showcasing three representative lexical units associated with diferent types Foofrce and their corresponding example sentences. This table not only demonstrates the diversitFyoorfce-related verbs captured in our study but also illustrates how these verbs are contextualized in natural language use. The full dataset of 100 entries provides a useful extension of the IS Catalogue, with a focFuosrocne image schema and its varied manifestations in language.
Following the generation and initial validation of our dataset, detailed in previous section, and shown in pink boxes in Figure1, we proceeded with a knowledge extraction process to formalize and integrate theForce-related information into existing semantic resources.
We employed the AMR2FRED tool to process these sentences. AMR2FRED is a sophisticated natural language processing tool that converts text into Abstract Meaning Representation (AMR) graphs, and then passes the graph to FRE3D3][ which performs several tasks, anong others: frame extraction, entity recognition, and entity alignment to DOLCE foundational o3n4t].oTlohgisyt[ool is particularly valuable for our purposes as it preserves the semantic richness of natural language while producing structured, machine-readable representations. F2isghuorwes the graph automatically generated from the sentence “The strong current ripped the swimmer’s goggles of her face.”
The RDF graphs generated by AMR2FRED for each sentence are collected and stored in a dedicated knowledge base. This knowledge base serves as a centralized repository of forFmoracleiz-erdelated semantic structures derived from our curated examples. To extract relevant entities from this knowledge base, we developed a targeted SPARQL query, shown in Fig4u.2r.eThis query is designed to identify and extract entities from PropBa3n5]k, [a lexical resource that provides a frame like structure and semantic role labels for English lexicon. Since the AMR2FRED graph is well formed RDF graph, the verb used in the sentence is reified as an instatiation of a specific occurrence (represented as an individual), havingrdf:type the PropBank entity on which it is disambiguated. The reasoning behind this is that an occurrence of a certain verb is the instatiation of the general concept of that verb (in our case), whic is represented on the graph via subsumption relation. The extracted entities represent concepts and actions directly associated withFotrhcee image schema as manifested in our dataset.
Finally, we enriched ImageSchemaNet, the existing ontology for image schemas, by adding these extracted entities as direct evocators Foofrtcheeimage schema. This addition was implemented in a separate graph within ImageSchemaNet, allowing for clear provenance and easy integration or separation of our contribution. This process not only augments ImageSchemaNet with new, empirically derivedForce-related concepts but also establishes a concrete link between abstract image schema theory and specific linguistic realizations of force.
SPARQL Query 1 SELECT DISTINCT ?e 2 WHERE { 3 ?e rdf:type ?pb_entity . 4 }
Box 4.2 SPARQL query to retrieve entities generated out of the original lexical unit in the graph, and the PropBank entity on which it is disambiguated.
The resulting enhanced ontology provides a valuable resource for researchers and practitioners working at the intersection of cognitive linguistics, natural language processing, and knowledge representation.
In this work, we have addressed the long-standing issue of underspecificationFoinrctehiemage schema. Our research has made significant strides in bridging the gap between abstract theoretical constructs and practical, operational applications. By employing a novel hybrid pipeline that combines large language model interactions, domain experts linguistic analysis, and knowledge extraction techniques, we have expanded upon Johnson’s initial categorizatiFoonrcoef types. Our methodology, which included domain exploration using Claude 3.5 Sonnet, generatFioorncoe-frelated verbs and contextual sentences, expert validation, and integration with existing semantic resources, has yielded several key achievements. First, we have developed a more nuanced and comprehensive understanding of theForce image schema, expanding beyond the original eight categories to include a wider range of force manifestations in language. Second, our approach has resulted in a validated dataset of 100 force-expressing verbs and their contextual uses, providing a valuable resource for future research in this area. Third, through the useAMoRf2FRED tool processing anSdPARQL querying, we have successfully integrated our findings into ImageSchemaNet, enhancing this ontology with empiricallyFodrecreiv-ed related concepts. This integration establishes a concrete link between image schema theory and specific linguistic realizationsFoorfce, opening new avenues for applications in natural language processing, knowledge representation, and cognitive computing. This work was supported by the Future Artificial Intelligence Research (FAIR) project, code PE00000013 CUP 53C22003630006. [22] A. Papafragou, C. Massey, L. Gleitman, When English proposes what Greek presupposes: The cross-linguistic encoding of motion events, Cognition 98 (2006) B75–B87. [23] J. A. Prieto Velasco, M. Tercedor Sánchez, The embodied nature of medical concepts: image schemas and language for pain., Cognitive processing (20141).0d.o1i0:07/s10339-013-0594-9. [24] D. Gromann, M. M. Hedblom, Body-mind-language: Multilingual knowledge extraction based on embodied cognition, in: AIC, 2017, pp. 20–33. [25] D. Gromann, M. M. Hedblom, Kinesthetic mind reader: A method to identify image schemas in natural language, in: Proceedings of Advancements in Cogntivie Systems, 2017. [26] L. Wachowiak, D. Gromann, Systematic analysis of image schemas in natural language through explainable multilingual neural language processing, in: Proceedings of the 29th International Conference on Computational Linguistics, 2022, pp. 5571–5581. [27] P. Lewis, E. Perez, A. Piktus, F. Petroni, V. Karpukhin, N. Goyal, H. Küttler, M. Lewis, W.-t. Yih, T. Rocktäschel, et al., Retrieval-augmented generation for knowledge-intensive nlp tasks, Advances in Neural Information Processing Systems 33 (2020) 9459–9474. [28] D. Edge, H. Trinh, N. Cheng, J. Bradley, A. Chao, A. Mody, S. Truitt, J. Larson, From local to global:
A graph rag approach to query-focused summarization, arXiv preprint arXiv:2404.16130 (2024). [29] J. Hurtienne, S. Huber, C. Baur, Supporting user interface design with image schemas: The iscat database as a research tool., in: ISD, 2022. [30] A. GANGEMI, et al., Amr2fred, a tool for translating abstract meaning representation to motifbased linguistic knowledge graph, in: Proceedings of the Extended Semantic Web Conference (ESWC2017), DEU, 2017, pp. 43–47. [31] A. Meloni, D. Reforgiato Recupero, A. Gangemi, Amr2fred, a tool for translating abstract meaning representation to motif-based linguistic knowledge graphs, in: The Semantic Web: ESWC 2017 Satellite Events: ESWC 2017 Satellite Events, Portorož, Slovenia, May 28–June 1, 2017, Revised Selected Papers 14, Springer, 2017, pp. 43–47. [32] S. De Giorgis, Ethics in the flesh: formalizing moral values in embodied cognition (2023). [33] A. Gangemi, V. Presutti, D. Reforgiato Recupero, A. G. Nuzzolese, F. Draicchio, M. Mongiovì,
Semantic web machine reading with fred, Semantic Web 8 (2017) 873–893. [34] S. Borgo, R. Ferrario, A. Gangemi, N. Guarino, C. Masolo, D. Porello, E. M. Sanfilippo, L. Vieu, Dolce: A descriptive ontology for linguistic and cognitive engineering, Applied ontology 17 (2022) 45–69. [35] S. Pradhan, J. Bonn, S. Myers, K. Conger, T. O’gorman, J. Gung, K. Wright-Bettner, M. Palmer, Propbank comes of age—larger, smarter, and more diverse, in: Proceedings of the 11th joint conference on lexical and computational semantics, 2022, pp. 278–288.