Representing image captions as concept graphs using semantic information

Conceptual interpretation of languages has gathered peak interest in the world of artificial intelligence. The challenge in modeling various complications involved in a language is the main motivation behind our work. Our main focus in this work is to develop conceptual graphical representation for image captions. We have used discourse representation structure to gain semantic information which is further modeled into a graphical structure. The effectiveness of the model is evaluated by a caption based image retrieval system. The image retrieval is performed by computing subgraph based similarity measures. Best retrievals were given an average rating of . ± . out of 4 by a group of 25 human judges. The experiments were performed on a subset of the SBU Captioned Photo Dataset. This purpose of this work is to establish the cognitive sensibility of the approach to caption representations

Representing image captions as concept graphs using semantic information

Conceptual interpretation of languages has gathered peak interest in the world of artificial intelligence. The challenge in modeling various complications involved in a language is the main motivation behind our work. Our main focus in this work is to develop conceptual graphical representation for image captions. We have used discourse representation structure to gain semantic information which is further modeled into a graphical structure. The effectiveness of the model is evaluated by a caption based image retrieval system. The image retrieval is performed by computing subgraph based similarity measures. Best retrievals were given an average rating of . ± . out of 4 by a group of 25 human judges. The experiments were performed on a subset of the SBU Captioned Photo Dataset. This purpose of this work is to establish the cognitive sensibility of the approach to caption representations.

Simplicial Complexes From Graphs Toward Graph Persistence

Persistent homology is a branch of computational topology which uses geometry and topology for shape description and analysis. This dissertation is an introductory study to link persistent homology and graph theory, the connection being represented by various methods to build simplicial complexes from a graph. The methods we consider are the complex of cliques, of independent sets, of neighbours, of enclaveless sets and complexes from acyclic subgraphs, each revealing several properties of the underlying graph. Moreover, we apply the core ideas of persistence theory in the new context of graph theory, we define the persistent block number and the persistent edge-block number.

Edge-aware Graph Attention Networks: Joint Reasoning On Text and Knowledge Graphs for Biomedical Question Answering

Much of the real-world dataset, including textual data, can be represented using graph structures. The use of graphs to represent textual data has many advantages, mainly related to maintaining a more significant amount of information, such as the relationships between words and their types. In recent years, many neural network architectures have been proposed to deal with tasks on graphs. Many of them consider only node features, ignoring or not giving the proper relevance to relationships between them. However, in many node classification tasks, they play a fundamental role. This thesis aims to analyze the main GNNs, evaluate their advantages and disadvantages, propose an innovative solution considered as an extension of GAT, and apply them to a case study in the biomedical field. We propose the reference GNNs, implemented with methodologies later analyzed, and then applied to a question answering system in the biomedical field as a replacement for the pre-existing GNN. We attempt to obtain better results by using models that can accept as input both node and edge features. As shown later, our proposed models can beat the original solution and define the state-of-the-art for the task under analysis.

GENEOs, compactifications, and graphs

Our objective in this thesis is to study the pseudo-metric and topological structure of the space of group equivariant non-expansive operators (GENEOs). We introduce the notions of compactification of a perception pair, collectionwise surjectivity, and compactification of a space of GENEOs. We obtain some compactification results for perception pairs and the space of GENEOs. We show that when the data spaces are totally bounded and endow the common domains with metric structures, the perception pairs and every collectionwise surjective space of GENEOs can be embedded isometrically into the compact ones through compatible embeddings. An important part of the study of topology of the space of GENEOs is to populate it in a rich manner. We introduce the notion of a generalized permutant and show that this concept too, like that of a permutant, is useful in defining new GENEOs. We define the analogues of some of the aforementioned concepts in a graph theoretic setting, enabling us to use the power of the theory of GENEOs for the study of graphs in an efficient way. We define the notions of a graph perception pair, graph permutant, and a graph GENEO. We develop two models for the theory of graph GENEOs. The first model addresses the case of graphs having weights assigned to their vertices, while the second one addresses weighted on the edges. We prove some new results in the proposed theory of graph GENEOs and exhibit the power of our models by describing their applications to the structural study of simple graphs. We introduce the concept of a graph permutant and show that this concept can be used to define new graph GENEOs between distinct graph perception pairs, thereby enabling us to populate the space of graph GENEOs in a rich manner and shed more light on its structure.

Essays on risk-taking in corporate finance

This thesis consists of three independent essays on risk-taking in corporate finance. The first essay explores how community-level social capital (CSC), framed as a cultural characteristic of individuals born in different provinces of Italy, affects investment behavior in equity crowdfunding. Results show that investors born in high-CSC provinces invest more money in ventures characterized by an enhanced risk profile. Observed risk-taking is theoretically linked to higher generalized trust endowed to people born in high-CSC areas. The second essay focuses on how convexity of Chief Financial Officers’ stock options affects their hedging decisions in the oil and gas industry. Highly convex CFOs hedge less commodity price risk, even if the Chief Executive Officer’s incentives are consistent with a more conservative hedging strategy. Finally, the third essay is a systematic literature review on how different sources of compensation-based risk-taking incentives of Chief Executive Officers affect decision-making in corporate finance.

Ethics in the flesh: formalizing moral values in embodied cognition

Values are beliefs or principles that are deemed significant or desirable within a specific society or culture, serving as the fundamental underpinnings for ethical and socio-behavioral norms. The objective of this research is to explore the domain encompassing moral, cultural, and individual values. To achieve this, we employ an ontological approach to formally represent the semantic relations within the value domain. The theoretical framework employed adopts Fillmore’s frame semantics, treating values as semantic frames. A value situation is thus characterized by the co-occurrence of specific semantic roles fulfilled within a given event or circumstance. Given the intricate semantics of values as abstract entities with high social capital, our investigation extends to two interconnected domains. The first domain is embodied cognition, specifically image schemas, which are cognitive patterns derived from sensorimotor experiences that shape our conceptualization of entities in the world. The second domain pertains to emotions, which are inherently intertwined with the realm of values. Consequently, our approach endeavors to formalize the semantics of values within an embodied cognition framework, recognizing values as emotional-laden semantic frames. The primary ontologies proposed in this work are: (i) ValueNet, an ontology network dedicated to the domain of values; (ii) ISAAC, the Image Schema Abstraction And Cognition ontology; and (iii) EmoNet, an ontology for theories of emotions. The knowledge formalization adheres to established modeling practices, including the reuse of semantic web resources such as WordNet, VerbNet, FrameNet, DBpedia, and alignment to foundational ontologies like DOLCE, as well as the utilization of Ontology Design Patterns. These ontological resources are operationalized through the development of a fully explainable frame-based detector capable of identifying values, emotions, and image schemas generating knowledge graphs from from natural language, leveraging the semantic dependencies of a sentence, and allowing non trivial higher layer knowledge inferences.

Supporting requirement elicitation and ontology testing in knowledge graph engineering

Knowledge graphs and ontologies are closely related concepts in the field of knowledge representation. In recent years, knowledge graphs have gained increasing popularity and are serving as essential components in many knowledge engineering projects that view them as crucial to their success. The conceptual foundation of the knowledge graph is provided by ontologies. Ontology modeling is an iterative engineering process that consists of steps such as the elicitation and formalization of requirements, the development, testing, refactoring, and release of the ontology. The testing of the ontology is a crucial and occasionally overlooked step of the process due to the lack of integrated tools to support it. As a result of this gap in the state-of-the-art, the testing of the ontology is completed manually, which requires a considerable amount of time and effort from the ontology engineers. The lack of tool support is noticed in the requirement elicitation process as well. In this aspect, the rise in the adoption and accessibility of knowledge graphs allows for the development and use of automated tools to assist with the elicitation of requirements from such a complementary source of data. Therefore, this doctoral research is focused on developing methods and tools that support the requirement elicitation and testing steps of an ontology engineering process. To support the testing of the ontology, we have developed XDTesting, a web application that is integrated with the GitHub platform that serves as an ontology testing manager. Concurrently, to support the elicitation and documentation of competency questions, we have defined and implemented RevOnt, a method to extract competency questions from knowledge graphs. Both methods are evaluated through their implementation and the results are promising.

Esprimere incertezza, ipotesi, dubbi in RDF con le Congetture

La semantica di RDF non permette di esprimere punti di vista contraddittori sullo stesso set di dati. Il problema consiste sostanzialmente nell’impossibilità di esprimere, in RDF, affermazioni il cui valore di verità sia sconosciuto, oppure in contrasto con quello di altre affermazioni, senza però asserirle, poichè questo le renderebbe indubbiamente vere. Nel corso del tempo, partendo dalla necessità di esprimere statement su altri statement, sono stati prodotti diversi approcci, nessuno dei quali sembra dare una risposta convincente all’esigenza che potremmo riassumere nel poter esprimere senza asserire. Nel presente lavoro, dopo un'analisi dei differenti approcci al problema, e dei relativi risultati, verranno presentate le "Congetture": una nuova proposta di estensione di RDF 1.1 che permette l’espressione di grafi il cui valore di verità è sconosciuto. Le Congetture sono una notazione per esprimere, senza asserire, named graphs in RDF, unitamente ad un meccanismo per affermarne la verità chiamato "collasso alla realtà". Una Congettura collassata è allo stesso tempo un grafo congetturale e un grafo asserito, ed è un modo semplice per gestire situazioni che, espresse inizialmente sotto forma di congetture, devono successivamente essere considerare vere. La proposta è costruita attorno a due concetti principali: 1) la Congettura: un concetto il cui valore di verità non è disponibile; 2) il collasso alla realtà: un meccanismo per asserire pienamente, in RDF, quando necessario, il valore di verità della Congettura. Verranno analizzati scenari avanzati quali Congetture di Congetture, Congetture di collassi e collassi a cascata. Verrà delineata la semantica formale completa della proposta, estendendo la simple interpretation di RDF 1.1, dimostrando che le Congetture sono pienamente compatibili con RDF. Le Congetture, con un'estensione minima del modello, aggiungono ad RDF la possibilità di esprimere, senza asserire, incertezze, ipotesi e dubbi.

A study of brain functional connectivity and cognitive processes in long COVID-19 patients

In this work, a prospective study conducted at the IRCCS Istituto delle Scienze Neurologiche di Bologna is presented. The aim was to investigate the brain functional connectivity of a cohort of patients (N=23) suffering from persistent olfactory dysfunction after SARS-CoV-2 infection (Post-COVID-19 syndrome), as compared to a matching group of healthy controls (N=26). In particular, starting from individual resting state functional-MRI data, different analytical approaches were adopted in order to find potential alterations in the connectivity patterns of patients’ brains. Analyses were conducted both at a whole-brain level and with a special focus on brain regions involved in the processing of olfactory stimuli (Olfactory Network). Statistical correlations between functional connectivity alterations and the results of olfactory and neuropsychological tests were investigated, to explore the associations with cognitive processes. The three approaches implemented for the analysis were the seed-based correlation analysis, the group-level Independent Component analysis and a graph-theoretical analysis of brain connectivity. Due to the relative novelty of such approaches, many implementation details and methodologies are not standardized yet and represent active research fields. Seed-based and group-ICA analyses’ results showed no statistically significant differences between groups, while relevant alterations emerged from those of the graph-based analysis. In particular, patients’ olfactory sub-graph appeared to have a less pronounced modular structure compared to the control group; locally, a hyper-connectivity of the right thalamus was observed in patients, with significant involvement of the right insula and hippocampus. Results of an exploratory correlation analysis showed a positive correlation between the graphs global modularity and the scores obtained in olfactory tests and negative correlations between the thalamus hyper-connectivity and memory tests scores.

Quantum Riemannian geometry on graphs for gauge field theory

In questo lavoro estendiamo concetti classici della geometria Riemanniana al fine di risolvere le equazioni di Maxwell sul gruppo delle permutazioni $S_3$. Cominciamo dando la strutture algebriche di base e la definizione di calcolo differenziale quantico con le principali proprietà. Generalizziamo poi concetti della geometria Riemanniana, quali la metrica e l'algebra esterna, al caso quantico. Tutto ciò viene poi applicato ai grafi dando la forma esplicita del calcolo differenziale quantico su $\mathbb{K}(V)$, della metrica e Laplaciano del secondo ordine e infine dell'algebra esterna. A questo punto, riscriviamo le equazioni di Maxwell in forma geometrica compatta usando gli operatori e concetti della geometria differenziale su varietà che abbiamo generalizzato in precedenza. In questo modo, considerando l'elettromagnetismo come teoria di gauge, possiamo risolvere le equazioni di Maxwell su gruppi finiti oltre che su varietà differenziabili. In particolare, noi le risolviamo su $S_3$.

Spectral methods in geometric deep learning

Questa tesi propone una panoramica sul funzionamento interno delle architetture alla base del deep learning e in particolare del geometric deep learning. Iniziando a discutere dalla storia degli algoritmi di intelligenza artificiale, vengono introdotti i principali costituenti di questi. In seguito vengono approfonditi alcuni elementi della teoria dei grafi, in particolare il concetto di laplaciano discreto e il suo ruolo nello studio del fenomeno di diffusione sui grafi. Infine vengono presentati alcuni algoritmi utilizzati nell'ambito del geometric deep learning su grafi per la classificazione di nodi. I concetti discussi vengono poi applicati nella realizzazione di un'architettura in grado di classficiare i nodi del dataset Zachary Karate Club.

Problems in physics and mathematics contexts with middle and high school classes: vertical and horizontal comparison

My thesis falls within the framework of physics education and teaching of mathematics. The objective of this report was made possible by using geometrical (in mathematics) and qualitative (in physics) problems. We have prepared four (resp. three) open answer exercises for mathematics (resp. physics). The test batch has been selected across two different school phases: end of the middle school (third year, 8\textsuperscript{th} grade) and beginning of high school (second and third year, 10\textsuperscript{th} and 11\textsuperscript{th} grades respectively). High school students achieved the best results in almost every problem, but 10\textsuperscript{th} grade students got the best overall results. Moreover, a clear tendency to not even try qualitative problems resolution has emerged from the first collection of graphs, regardless of subject and grade. In order to improve students' problem-solving skills, it is worth to invest on vertical learning and spiral curricula. It would make sense to establish a stronger and clearer connection between physics and mathematical knowledge through an interdisciplinary approach.

Bio-QA-GNN: Reasoning with Language Models and Knowledge Graphs for Interpretable Biomedical Question Answering

Nowadays the idea of injecting world or domain-specific structured knowledge into pre-trained language models (PLMs) is becoming an increasingly popular approach for solving problems such as biases, hallucinations, huge architectural sizes, and explainability lack—critical for real-world natural language processing applications in sensitive fields like bioinformatics. One recent work that has garnered much attention in Neuro-symbolic AI is QA-GNN, an end-to-end model for multiple-choice open-domain question answering (MCOQA) tasks via interpretable text-graph reasoning. Unlike previous publications, QA-GNN mutually informs PLMs and graph neural networks (GNNs) on top of relevant facts retrieved from knowledge graphs (KGs). However, taking a more holistic view, existing PLM+KG contributions mainly consider commonsense benchmarks and ignore or shallowly analyze performances on biomedical datasets. This thesis start from a propose of a deep investigation of QA-GNN for biomedicine, comparing existing or brand-new PLMs, KGs, edge-aware GNNs, preprocessing techniques, and initialization strategies. By combining the insights emerged in DISI's research, we introduce Bio-QA-GNN that include a KG. Working with this part has led to an improvement in state-of-the-art of MCOQA model on biomedical/clinical text, largely outperforming the original one (+3.63\% accuracy on MedQA). Our findings also contribute to a better understanding of the explanation degree allowed by joint text-graph reasoning architectures and their effectiveness on different medical subjects and reasoning types. Codes, models, datasets, and demos to reproduce the results are freely available at: \url{https://github.com/disi-unibo-nlp/bio-qagnn}.

Pipkiiα Is Widely Expressed In Hematopoietic-derived Cells And May Play A Role In The Expression Of Alpha- And Gamma-globins In K562 Cells.

Characterized for the first time in erythrocytes, phosphatidylinositol phosphate kinases (PIP kinases) belong to a family of enzymes that generate various lipid messengers and participate in several cellular processes, including gene expression regulation. Recently, the PIPKIIα gene was found to be differentially expressed in reticulocytes from two siblings with hemoglobin H disease, suggesting a possible relationship between PIPKIIα and the production of globins. Here, we investigated PIPKIIα gene and protein expression and protein localization in hematopoietic-derived cells during their differentiation, and the effects of PIPKIIα silencing on K562 cells. PIPKIIα silencing resulted in an increase in α and γ globins and a decrease in the proliferation of K562 cells without affecting cell cycle progression and apoptosis. In conclusion, using a cell line model, we showed that PIPKIIα is widely expressed in hematopoietic-derived cells, is localized in their cytoplasm and nucleus, and is upregulated during erythroid differentiation. We also showed that PIPKIIα silencing can induce α and γ globin expression and decrease cell proliferation in K562 cells.