Search

Semantic Knowledge Graphs (SKG) face challenges with scalability, flexibility, contextual understanding, and handling unstructured or ambiguous information. However, they offer formal and structured knowledge enabling highly interpretable and reliable results by means of reasoning and querying. Large Language Models (LLMs) overcome those limitations making them suitable in open-ended tasks and unstructured environments. Nevertheless, LLMs are neither interpretable nor reliable. To solve the dichotomy between LLMs and SKGs we envision Logic Augmented Generation (LAG) that combines the benefits of the two worlds. LAG uses LLMs as Reactive Continuous Knowledge Graphs that can generate potentially infinite relations and tacit knowledge on-demand. SKGs are key for injecting a discrete heuristic dimension with clear logical and factual boundaries. We exemplify LAG in two tasks of collective intelligence, i.e., medical diagnostics and climate projections. Understanding the properties and limitations of LAG, which are still mostly unknown, is of utmost importance for enabling a variety of tasks involving tacit knowledge in order to provide interpretable and effective results., Comment: 10 pages, 2 figures

The development of artificial intelligence systems capable of understanding and reasoning about complex real-world scenarios is a significant challenge. In this work we present a novel approach to enhance and exploit LLM reactive capability to address complex problems and interpret deeply contextual real-world meaning. We introduce a method and a tool for creating a multimodal, knowledge-augmented formal representation of meaning that combines the strengths of large language models with structured semantic representations. Our method begins with an image input, utilizing state-of-the-art large language models to generate a natural language description. This description is then transformed into an Abstract Meaning Representation (AMR) graph, which is formalized and enriched with logical design patterns, and layered semantics derived from linguistic and factual knowledge bases. The resulting graph is then fed back into the LLM to be extended with implicit knowledge activated by complex heuristic learning, including semantic implicatures, moral values, embodied cognition, and metaphorical representations. By bridging the gap between unstructured language models and formal semantic structures, our method opens new avenues for tackling intricate problems in natural language understanding and reasoning.

This work explores the integration of ontology-based reasoning and Machine Learning techniques for explainable value classification. By relying on an ontological formalization of moral values as in the Moral Foundations Theory, relying on the DnS Ontology Design Pattern, the \textit{sandra} neuro-symbolic reasoner is used to infer values (fomalized as descriptions) that are \emph{satisfied by} a certain sentence. Sentences, alongside their structured representation, are automatically generated using an open-source Large Language Model. The inferred descriptions are used to automatically detect the value associated with a sentence. We show that only relying on the reasoner's inference results in explainable classification comparable to other more complex approaches. We show that combining the reasoner's inferences with distributional semantics methods largely outperforms all the baselines, including complex models based on neural network architectures. Finally, we build a visualization tool to explore the potential of theory-based values classification, which is publicly available at http://xmv.geomeaning.com/., Comment: Published at ESWC24 Satellite Event

The task of detecting moral values in text has significant implications in various fields, including natural language processing, social sciences, and ethical decision-making. Previously proposed supervised models often suffer from overfitting, leading to hyper-specialized moral classifiers that struggle to perform well on data from different domains. To address this issue, we introduce novel systems that leverage abstract concepts and common-sense knowledge acquired from Large Language Models and Natural Language Inference models during previous stages of training on multiple data sources. By doing so, we aim to develop versatile and robust methods for detecting moral values in real-world scenarios. Our approach uses the GPT 3.5 model as a zero-shot ready-made unsupervised multi-label classifier for moral values detection, eliminating the need for explicit training on labeled data. We compare it with a smaller NLI-based zero-shot model. The results show that the NLI approach achieves competitive results compared to the Davinci model. Furthermore, we conduct an in-depth investigation of the performance of supervised systems in the context of cross-domain multi-label moral value detection. This involves training supervised models on different domains to explore their effectiveness in handling data from different sources and comparing their performance with the unsupervised methods. Our contributions encompass a thorough analysis of both supervised and unsupervised methodologies for cross-domain value detection. We introduce the Davinci model as a state-of-the-art zero-shot unsupervised moral values classifier, pushing the boundaries of moral value detection without the need for explicit training on labeled data. Additionally, we perform a comparative evaluation of our approach with the supervised models, shedding light on their respective strengths and weaknesses.

World modelling, i.e. building a representation of the rules that govern the world so as to predict its evolution, is an essential ability for any agent interacting with the physical world. Recent applications of the Transformer architecture to the problem of world modelling from video input show notable improvements in sample efficiency. However, existing approaches tend to work only at the image level thus disregarding that the environment is composed of objects interacting with each other. In this paper, we propose an architecture combining Transformers for world modelling with the slot-attention paradigm, an approach for learning representations of objects appearing in a scene. We describe the resulting neural architecture and report experimental results showing an improvement over the existing solutions in terms of sample efficiency and a reduction of the variation of the performance over the training examples. The code for our architecture and experiments is available at https://github.com/torchipeppo/transformers-and-slot-encoding-for-wm

This paper presents sandra, a neuro-symbolic reasoner combining vectorial representations with deductive reasoning. Sandra builds a vector space constrained by an ontology and performs reasoning over it. The geometric nature of the reasoner allows its combination with neural networks, bridging the gap with symbolic knowledge representations. Sandra is based on the Description and Situation (DnS) ontology design pattern, a formalization of frame semantics. Given a set of facts (a situation) it allows to infer all possible perspectives (descriptions) that can provide a plausible interpretation for it, even in presence of incomplete information. We prove that our method is correct with respect to the DnS model. We experiment with two different tasks and their standard benchmarks, demonstrating that, without increasing complexity, sandra (i) outperforms all the baselines (ii) provides interpretability in the classification process, and (iii) allows control over the vector space, which is designed a priori.

Emotions are a subject of intense debate in various disciplines. Despite the proliferation of theories and definitions, there is still no consensus on what emotions are, and how to model the different concepts involved when we talk about - or categorize - them. In this paper, we propose an OWL frame-based ontology of emotions: the Emotion Frames Ontology (EFO). EFO treats emotions as semantic frames, with a set of semantic roles that capture the different aspects of emotional experience. EFO follows pattern-based ontology design, and is aligned to the DOLCE foundational ontology. EFO is used to model multiple emotion theories, which can be cross-linked as modules in an Emotion Ontology Network. In this paper, we exemplify it by modeling Ekman's Basic Emotions (BE) Theory as an EFO-BE module, and demonstrate how to perform automated inferences on the representation of emotion situations. EFO-BE has been evaluated by lexicalizing the BE emotion frames from within the Framester knowledge graph, and implementing a graph-based emotion detector from text. In addition, an EFO integration of multimodal datasets, including emotional speech and emotional face expressions, has been performed to enable further inquiry into crossmodal emotion semantics.

General features of the $\alpha-\beta$ transition of quartz are investigated. Molecular dynamics methods are mainly used, an analytic treatment being deferred to a work in preparation. A basic preliminary observation is that the transition involves only a subsystem of four normal modes on which the remaining ones just act as a reservoir. The dynamics of the relevant subsystem turns out to be Hamiltonian, being governed by an effective potential that depends on the specific energy of the total system. The effective potential is actually calculated through time averages. It describes the transition as a pitchfork bifurcation, and also explains the phenomenon of the soft mode, since it exhibits a frequency that vanishes at the transition. The critical exponent too is estimated., Comment: 14 pages, 4 figures

What should a data integration framework for knowledge engineers look like? Recent research on Knowledge Graph construction proposes the design of a fa\c{c}ade, a notion borrowed from object-oriented software engineering. This idea is applied to SPARQL Anything, a system that allows querying heterogeneous resources as-if they were in RDF, in plain SPARQL 1.1, by overloading the SERVICE clause. SPARQL Anything supports a wide variety of file formats, from popular ones (CSV, JSON, XML, Spreadsheets) to others that are not supported by alternative solutions (Markdown, YAML, DOCx, Bibtex). Features include querying Web APIs with high flexibility, parametrised queries, and chaining multiple transformations into complex pipelines. In this paper, we describe the design rationale and software architecture of the SPARQL Anything system. We provide references to an extensive set of reusable, real-world scenarios from various application domains. We report on the value-to-users of the founding assumptions of its design, compared to alternative solutions through a community survey and a field report from the industry., Comment: 15 pages

DOLCE, the first top-level (foundational) ontology to be axiomatized, has remained stable for twenty years and today is broadly used in a variety of domains. DOLCE is inspired by cognitive and linguistic considerations and aims to model a commonsense view of reality, like the one human beings exploit in everyday life in areas as diverse as socio-technical systems, manufacturing, financial transactions and cultural heritage. DOLCE clearly lists the ontological choices it is based upon, relies on philosophical principles, is richly formalized, and is built according to well-established ontological methodologies, e.g. OntoClean. Because of these features, it has inspired most of the existing top-level ontologies and has been used to develop or improve standards and public domain resources (e.g. CIDOC CRM, DBpedia and WordNet). Being a foundational ontology, DOLCE is not directly concerned with domain knowledge. Its purpose is to provide the general categories and relations needed to give a coherent view of reality, to integrate domain knowledge, and to mediate across domains. In these 20 years DOLCE has shown that applied ontologies can be stable and that interoperability across reference and domain ontologies is a reality. This paper briefly introduces the ontology and shows how to use it on a few modeling cases., Comment: 25 pages, 7 figures

In this paper we propose the Music Note Ontology, an ontology for modelling music notes and their realisation. The ontology addresses the relation between a note represented in a symbolic representation system, and its realisation, i.e. a musical performance. This work therefore aims to solve the modelling and representation issues that arise when analysing the relationships between abstract symbolic features and the corresponding physical features of an audio signal. The ontology is composed of three different Ontology Design Patterns (ODP), which model the structure of the score (Score Part Pattern), the note in the symbolic notation (Music Note Pattern) and its realisation (Musical Object Pattern)., Comment: 12 pages, 1 figure, 1 table. Proceedings of the 12th Workshop on Ontology Design and Patterns (WOP 2021), Online, edited by K. Hammar et al., 2021

Values, as intended in ethics, determine the shape and validity of moral and social norms, grounding our everyday individual and community behavior on commonsense knowledge. Formalising latent moral content in human interaction is an appealing perspective that would enable a deeper understanding of both social dynamics and individual cognitive and behavioral dimension. To tackle this problem, several theoretical frameworks offer different values models, and organize them into different taxonomies. The problem of the most used theories is that they adopt a cultural-independent perspective while many entities that are considered "values" are grounded in commonsense knowledge and expressed in everyday life interaction. We propose here two ontological modules, FOLK, an ontology for values intended in their broad sense, and That's All Folks, a module for lexical and factual folk value triggers, whose purpose is to complement the main theories, providing a method for identifying the values that are not contemplated by the major value theories, but which nonetheless play a key role in daily human interactions, and shape social structures, cultural biases, and personal beliefs. The resource is tested via performing automatic detection of values from text with a frame-based approach., Comment: 16 pages, conference paper

We present a new dispute resolution protocol that can be built on the Ethereum blockchain. Unlike existing applications like Kleros, privacy is ensured by design through the use of the zero-knowledge protocols Semaphore and MACI (Minimal Anti-Collusion Infrastructure), which provide, among other things, resistance to Sybil-like attacks and corruption. Differently from Kleros, dispute resolution is guaranteed despite the users having the final say. Moreover, the proposed model does not use a native token on the platform, but aims to reward stakeholders through a social incentive mechanism based on soulbound tokens, introduced by Weyl, Ohlhaver, and Buterin in 2022. Users with these tokens will be considered trustworthy and will have the ability to govern the platform. As far as we know, this is one of the first blockchain projects that seeks to introduce social governance rather than one based on economic incentives.

In recent years, there has been an exponential growth of applications, including dialogue systems, that handle sensitive personal information. This has brought to light the extremely important issue of personal data protection in virtual environments. Sensitive Information Detection (SID) approaches different domains and languages in literature. However, if we refer to the personal data domain, a shared benchmark or the absence of an available labeled resource makes comparison with the state-of-the-art difficult. We introduce and release SPeDaC , a new annotated resource for the identification of sensitive personal data categories in the English language. SPeDaC enables the evaluation of computational models for three different SID subtasks with increasing levels of complexity. SPeDaC 1 regards binary classification, a model has to detect if a sentence contains sensitive information or not; whereas, in SPeDaC 2 we collected labeled sentences using 5 categories that relate to macro-domains of personal information; in SPeDaC 3, the labeling is fine-grained (61 personal data categories). We conduct an extensive evaluation of the resource using different state-of-the-art-classifiers. The results show that SPeDaC is challenging, particularly with regard to fine-grained classification. The transformer models achieve the best results (acc. RoBERTa on SPeDaC 1 = 98.20%, DeBERTa on SPeDaC 2 = 95.81% and SPeDaC 3 = 77.63%)., Comment: 25 pages, 4 figures, 12 tables

Proof-of-Work (PoW) is a popular consensus protocol used by Bitcoin since its inception. PoW has the well-known flaw of assigning all the reward to the single miner (or pool) that inserts the new block. This has the consequence of making the variance of the reward and thus the mining enterprise risk extremely high. To address this problem, Shi in 2016 proposed a theoretical algorithm that would substantially reduce the issue. We introduce a variant of Proof-of-Work that improves on Shi's idea and can be easily implemented in practice. In order to insert a block, the network must not find a single nonce, but must find a few of them. This small change allows for a fairer distribution of rewards and at the same time has the effect of regularizing the insertion time of blocks. This would facilitate the emergence of small pools or autonomous miners.

In 2020 Sala, Sogiorno and Taufer have been able to find the private keys of some Bitcoin addresses, thus being able to spend the cryptocurrency linked to them. This result was unexpected, since the recovery of non-trivial private keys for blockchain addresses is deemed to be an infeasible problem. In this paper we widen this analysis by mounting a similar attack to other small subsets of the set of private keys. We then apply it to other blockchains as well, examining Ethereum, Dogecoin, Litecoin, Dash, Zcash and Bitcoin Cash. In addition to the results, we also explain the techniques we have used to perform this exhaustive search for all the addresses that have ever appeared in these blockchains., Comment: 13 pages

We present the Frame-based ontology Design Outlet (FrODO), a novel method and tool for drafting ontologies from competency questions automatically. Competency questions are expressed as natural language and are a common solution for representing requirements in a number of agile ontology engineering methodologies, such as the eXtreme Design (XD) or SAMOD. FrODO builds on top of FRED. In fact, it leverages the frame semantics for drawing domain-relevant boundaries around the RDF produced by FRED from a competency question, thus drafting domain ontologies. We carried out a user-based study for assessing FrODO in supporting engineers for ontology design tasks. The study shows that FrODO is effective in this and the resulting ontology drafts are qualitative., Comment: 15 pages

The use of Semantic Technologies - in particular the Semantic Web - has revealed to be a great tool for describing the cultural heritage domain and artistic practices. However, the panorama of ontologies for musicological applications seems to be limited and restricted to specific applications. In this research, we propose HaMSE, an ontology capable of describing musical features that can assist musicological research. More specifically, HaMSE proposes to address sues that have been affecting musicological research for decades: the representation of music and the relationship between quantitative and qualitative data. To do this, HaMSE allows the alignment between different music representation systems and describes a set of musicological features that can allow the music analysis at different granularity levels.

Scholarly data is growing continuously containing information about the articles from a plethora of venues including conferences, journals, etc. Many initiatives have been taken to make scholarly data available as Knowledge Graphs (KGs). These efforts to standardize these data and make them accessible have also led to many challenges such as exploration of scholarly articles, ambiguous authors, etc. This study more specifically targets the problem of Author Name Disambiguation (AND) on Scholarly KGs and presents a novel framework, Literally Author Name Disambiguation (LAND), which utilizes Knowledge Graph Embeddings (KGEs) using multimodal literal information generated from these KGs. This framework is based on three components: 1) Multimodal KGEs, 2) A blocking procedure, and finally, 3) Hierarchical Agglomerative Clustering. Extensive experiments have been conducted on two newly created KGs: (i) KG containing information from Scientometrics Journal from 1978 onwards (OC-782K), and (ii) a KG extracted from a well-known benchmark for AND provided by AMiner (AMiner-534K). The results show that our proposed architecture outperforms our baselines of 8-14% in terms of the F1 score and shows competitive performances on a challenging benchmark such as AMiner. The code and the datasets are publicly available through Github: https://github.com/sntcristian/and-kge and Zenodo:https://doi.org/10.5281/zenodo.6309855 respectively.

In this work, we fill the gap in the Semantic Web in the context of Cultural Symbolism. Building upon earlier work in, we introduce the Simulation Ontology, an ontology that models the background knowledge of symbolic meanings, developed by combining the concepts taken from the authoritative theory of Simulacra and Simulations of Jean Baudrillard with symbolic structures and content taken from "Symbolism: a Comprehensive Dictionary" by Steven Olderr. We re-engineered the symbolic knowledge already present in heterogeneous resources by converting it into our ontology schema to create HyperReal, the first knowledge graph completely dedicated to cultural symbolism. A first experiment run on the knowledge graph is presented to show the potential of quantitative research on symbolism., Comment: 8 pages, 5 figures

Verifying the veracity of claims requires reasoning over a large knowledge base, often in the form of corpora of trustworthy sources. A common approach consists in retrieving short portions of relevant text from the reference documents and giving them as input to a natural language inference module that determines whether the claim can be inferred or contradicted from them. This approach, however, struggles when multiple pieces of evidence need to be collected and combined from different documents, since the single documents are often barely related to the target claim and hence they are left out by the retrieval module. We conjecture that a graph-based approach can be beneficial to identify fragmented evidence. We tested this hypothesis by building, over the whole corpus, a large graph that interconnects text portions by means of mentioned entities and exploiting such a graph for identifying candidate sets of evidence from multiple sources. Our experiments show that leveraging on a graph structure is beneficial in identifying a reasonably small portion of passages related to a claim.

We report the results of a numerical investigation, performed in the frame of dynamical systems' theory, for a realistic model of a ionic crystal for which, due to the presence of long--range Coulomb interactions, the Gibbs distribution is not well defined. Taking initial data with a Maxwell-Boltzmann distribution for the mode-energies $E_k$, we study the dynamical fluctuations, computing the moduli of the the energy-changes $|E_k(t)-E_k(0)|$. The main result is that they follow Tsallis distributions, which relax to distributions close to Maxwell-Boltzmann ones; indications are also given that the system remains correlated. The relaxation time $\tau$ depends on specific energy $\varepsilon$, and for the curve $\tau$ vs, $\varepsilon$ one has two results. First, there exists an energy threshold $\varepsilon_0$, above which the curve has the form $$ \tau \cdot \varepsilon \simeq h\ , $$ where, unexpectedly, Planck's constant $h$ shows up. In terms of the standard deviation $\Delta E$ of a mode-energy (for which one has $\Delta E=\varepsilon$), denoting by $\Delta t$ the relaxation time $\tau$, the relation reads $\Delta t \cdot \Delta E \simeq h$, which reminds of the Heisenberg uncertainty relation. Moreover, the threshold corresponds to zero-point energy. Indeed, the quantum value of the latter is $h\nu/2$ ( where $\nu$ is the characterisic infrared frequency of the system), while we find $\varepsilon \simeq h\nu/4$, so that one only has a discrepancy of a factor 2. So it seems that lack of full chaoticity manifests itself, in Statistical Thermodynamics, through quantum-like phenomena.