Abstract Despite significant progress in Embodied AI, current agents largely operate under generic task specifications and struggle to reason about user-specific semantics that naturally arise in human-centered environments. In domestic settings, objects are often associated with particular individuals, requiring agents to interpret personalized instructions such as ownership and preference when navigating and acting in 3D spaces. We introduce PersONAL-3D ( PERS onalized O bject N avigation A nd L ocalization), a benchmark designed to study personalized spatial reasoning in embodied environments. PersONAL-3D focuses on domestic scenarios in which an agent must navigate to target objects associated with specific individuals, given natural-language instructions such as “find Lily’s backpack” . The benchmark includes 2,000+ curated evaluation episodes across 30+ photorealistic HM3D homes. Each episode pairs a natural-language scene description that specifies object ownership with a user-specific query, requiring models to ground personalized semantics in 3D space. PersONAL-3D supports two evaluation settings: (1) Personalized Active Navigation in previously unseen environments, and (2) Personalized Object Grounding in pre-explored scenes or directly on 3D point clouds. Experiments with state-of-the-art baselines reveal a substantial gap to human performance, with the best navigation model underperforming humans by about 45 percentage points in Success Rate and 25 percentage points in Path Efficiency, indicating that current methods struggle to perceive, act, and reason over personalized information in embodied contexts. This work highlights personalization as a critical and largely unsolved challenge for embodied AI systems operating in real-world assistive scenarios.

In recent years, there has been a growing interest in using generative models for de novo drug design. State-of-the-Art methods typically focus on either 2D structures or 3D structures, also known as conformers. Designing 3D structures is more challenging because it involves predicting spatial coordinates, necessitating the use of SE(3) equivariant architectures to ensure consistency under coordinate transformations like rotations and translations. This study presents D4, a novel Distance and Discrete Denoising Diffusion model that utilizes the distance matrix of molecular atoms to predict a molecule’s 3D coordinates, which are naturally unaffected by such transformations. This method effectively sidesteps the difficulties encountered with traditional coordinate-based training done by State-of-the-Art methods and allows explicit conditioning of bond types on distances. The experiments performed on three well-established datasets — QM9, GDB13, and ZINC250K — of varying challenges show that this approach significantly surpasses the performance of MiDi, a State-of-the-Art approach for generating 3D molecular structures. Additionally, an ablation study confirms the significance of adopting a novel regularization loss, which addresses errors in distance predictions and bounds the triangle inequality, validating the use of distance matrices in molecular generative models. • Generation of 3D molecules through distance and discrete denoising diffusion • SE(3) equivariance is built into the model by the use of distances • A loss on eigenvalues leads to better generation of Euclidean Distance Matrices in 3D • D4 surpasses State-of-the-Art model in the generation of realistic dis- tances in QM9, ZINC, and GDB13 • KDEs offer additional qualitative insights, showing improved distribu- tion learning

Large Language Models (LLMs) have demonstrated excellent capabilities in composing various modules together to create programs that can perform complex reasoning tasks on images. In this paper, we propose TANGO, an approach that extends the program composition via LLMs already observed for images, aiming to integrate those capabilities into embodied agents capable of observing and acting in the world. Specifically, by employing a simple PointGoal Navigation model combined with a memory-based exploration policy as a foundational primitive for guiding an agent through the world, we show how a single model can address diverse tasks without additional training. We task an LLM with composing the provided primitives to solve a specific task, using only a few in-context examples in the prompt. We evaluate our approach on three key Embodied AI tasks: Open-Set ObjectGoal Navigation, Multi-Modal Lifelong Navigation, and Open Embodied Question Answering, achieving state-of-the-art results without any specific fine-tuning in challenging zero-shot scenarios.

Recent years have witnessed an increase in interest in leveraging generative models for de novo molecular design in drug discovery.Many State-of-the-Art (SotA) models incorporate the 3D structural information of the molecule, particularly atomic spatial coordinates.However, such approaches face challenges integrating SE(3) equivariance when trained on coordinates.This work explores the use of the distance matrix for molecular structures, natively SE(3) invariant, avoiding whatever the issue.Experimental evaluation shows that our proposed approach significantly improves upon MiDi, a SotA 3D molecule generator.

Weighted First Order Model Counting (WFOMC) is fundamental to probabilistic inference in statistical relational learning models. As WFOMC is known to be intractable in general (#P-complete), logical fragments that admit polynomial time WFOMC are of significant interest. Such fragments are called domain liftable . Recent works have shown that the two-variable fragment of first order logic extended with counting quantifiers (C 2 ) is domain-liftable. However, many properties of real-world data, like acyclicity in citation networks and connectivity in social networks, cannot be modeled in C 2 , or first order logic in general. In this work, we expand the domain liftability of C 2 with multiple such properties. We show that any C 2 sentence remains domain liftable when one of its relations is restricted to represent a directed acyclic graph, a connected graph, a tree (resp. a directed tree) or a forest (resp. a directed forest). All our results rely on a novel and general methodology of counting by splitting . Besides their application to probabilistic inference, our results provide a general framework for counting combinatorial structures. We expand a vast array of previous results in discrete mathematics literature on directed acyclic graphs, phylogenetic networks, etc.

Graph generative models can be classified into two prominent families: one-shot models, which generate a graph in one go, and sequential models, which generate a graph by successive additions of nodes and edges. Ideally, between these two extreme models lies a continuous range of models that adopt different levels of sequentiality. This paper proposes a graph generative model, called Insert-Fill-Halt (IFH), that supports the specification of a sequentiality degree. IFH is based upon the theory of Denoising Diffusion Probabilistic Models (DDPM), designing a node removal process that gradually destroys a graph. An insertion process learns to reverse this removal process by inserting arcs and nodes according to the specified sequentiality degree. We evaluate the performance of IFH in terms of quality, run time, and memory, depending on different sequentiality degrees. We also show that using DiGress, a diffusion-based one-shot model, as a generative step in IFH leads to improvement to the model itself, and is competitive with the current state-of-the-art.

We address the problem of learning planning domains from plan traces that are obtained by observing the environment states through noisy sensors. In such situations, approaches that assume correct traces are not applicable. We tackle the problem by designing a probabilistic graphical model where preconditions and effects of every planning domain operators, and traces’ observations are modeled by random variables. Probabilistic inference conditioned by the observed traces allows our approach to derive a posterior probability of an atom being a precondition and/or an effect of an operator. Planning domains are obtained either by sampling or by applying the maximum a posteriori criterion. We compare our approach with a frequentist baseline and the currently available state-of-the-art approaches. We measure the performance of each method according to two criteria: reconstruction of the original planning domain and effectiveness in solving new planning problems of the same domain. Our experimental analysis shows that our approach learns action models that are more accurate w.r.t. state-of-the-art approaches, and strongly outperforms other approaches in generating models that are effective for solving new problems.

Abstract Object detectors are used for searching all objects belonging to a pre-defined set of categories contained in a given picture. However, users are often not interested in finding all objects, but only those that pertain to a small set of categories or concepts. Nowadays, the standard approach to solve this task involves initially employing an object detector to identify all objects within the image, followed by refining the outcomes to retain only the ones of interest. Nevertheless, the object detector does not take advantage of the user’s prior intent that, when used, can potentially improve the detection performance of the model. This work presents a method to condition an existing object detector with the user’s intent, encoded as one or more concepts from the WordNet graph, to find just those objects of interest. The proposed approach takes advantage of existing datasets for object detection without the need for new annotations, and it allows to adapt the already existing object detector models with minor changes. The evaluation, performed on the COCO and the Visual Genome datasets considering several object detector architectures, shows that conditioning the search on concepts is actually beneficial. The code and the pre-trained model weights are released at: https://github.com/drigoni/Concept-Conditioned-Object-Detector .

Autonomous agents embedded in a physical environment need the ability to recognize objects and their properties from sensory data. Such a perceptual ability is often implemented by supervised machine learning models, which are pre-trained using a set of labelled data. In real-world, open-ended deployments, however, it is unrealistic to assume to have a pre-trained model for all possible environments. Therefore, agents need to dynamically learn/adapt/extend their perceptual abilities online, in an autonomous way, by exploring and interacting with the environment where they operate. This paper describes a way to do so, by exploiting symbolic planning. Specifically, we formalize the problem of automatically training a neural network to recognize object properties as a symbolic planning problem (using PDDL). We use planning techniques to produce a strategy for automating the training dataset creation and the learning process. Finally, we provide an experimental evaluation in both a simulated and a real environment, which shows that the proposed approach is able to successfully learn how to recognize new object properties.

Learning how to navigate among humans in an occluded and spatially constrained indoor environment, is a key ability required to embodied agents to be integrated into our society. In this paper, we propose an end-to-end architecture that exploits Proximity-Aware Tasks (referred as to Risk and Proximity Compass) to inject into a reinforcement learning navigation policy the ability to infer common-sense social behaviours. To this end, our tasks exploit the notion of immediate and future dangers of collision. Furthermore, we propose an evaluation protocol specifically designed for the Social Navigation Task in simulated environments. This is done to capture fine-grained features and characteristics of the policy by analyzing the minimal unit of human-robot spatial interaction, called Encounter. We validate our approach on Gibson4+ and Habitat-Matterport3D datasets.

Neuro-Symbolic (NeSy) integration combines symbolic reasoning with Neural Networks (NNs) for tasks requiring perception and reasoning. Most NeSy systems rely on continuous relaxation of logical knowledge, and no discrete decisions are made within the model pipeline. Furthermore, these methods assume that the symbolic rules are given. In this paper, we propose Deep Symboilic Learning (DSL), a NeSy system that learns NeSy-functions, i.e., the composition of a (set of) perception functions which map continuous data to discrete symbols, and a symbolic function over the set of symbols. DSL simultaneously learns the perception and symbolic functions while being trained only on their composition (NeSy-function). The key novelty of DSL is that it can create internal (interpretable) symbolic representations and map them to perception inputs within a differentiable NN learning pipeline. The created symbols are automatically selected to generate symbolic functions that best explain the data. We provide experimental analysis to substantiate the efficacy of DSL in simultaneously learning perception and symbolic functions.

Autonomous agents embedded in a physical environment need the ability to correctly perceive the state of the environment from sensory data. In partially observable environments, certain properties can be perceived only in specific situations and from certain viewpoints that can be reached by the agent by planning and executing actions. For instance, to understand whether a cup is full of coffee, an agent, equipped with a camera, needs to turn on the light and look at the cup from the top. When the proper situations to perceive the desired properties are unknown, an agent needs to learn them and plan to get in such situations. In this paper, we devise a general method to solve this problem by evaluating the confidence of a neural network online and by using symbolic planning. We experimentally evaluate the proposed approach on several synthetic datasets, and show the feasibility of our approach in a real-world scenario that involves noisy perceptions and noisy actions on a real robot.

Abstract Recent work has shown learning systems can use logical background knowledge to compensate for a lack of labeled training data. Many methods work by creating a loss function that encodes this knowledge. However, often the logic is discarded after training, even if it is still helpful at test time. Instead, we ensure neural network predictions satisfy the knowledge by refining the predictions with an extra computation step. We introduce differentiable refinement functions that find a corrected prediction close to the original prediction. We study how to effectively and efficiently compute these refinement functions. Using a new algorithm called iterative local refinement (ILR), we combine refinement functions to find refined predictions for logical formulas of any complexity. ILR finds refinements on complex SAT formulas in significantly fewer iterations and frequently finds solutions where gradient descent can not. Finally, ILR produces competitive results in the MNIST addition task.

Weighted First-Order Model Counting (WFOMC) computes the weighted sum of the models of a first-order logic theory on a given finite domain. First-Order Logic theories that admit polynomial-time WFOMC w.r.t domain cardinality are called domain liftable. We introduce the concept of lifted interpretations as a tool for formulating closed forms for WFOMC. Using lifted interpretations, we reconstruct the closed-form formula for polynomial-time FOMC in the universally quantified fragment of FO2, earlier proposed by Beame et al. We then expand this closed-form to incorporate cardinality constraints, existential quantifiers, and counting quantifiers (a.k.a C2) without losing domain-liftability. Finally, we show that the obtained closed-form motivates a natural definition of a family of weight functions strictly larger than symmetric weight functions.

In this paper, we present a novel approach to incrementally learn an Abstract Model of an unknown environment, and show how an agent can reuse the learned model for tackling the Object Goal Navigation task. The Abstract Model is a finite state machine in which each state is an abstraction of a state of the environment, as perceived by the agent in a certain position and orientation. The perceptions are high-dimensional sensory data (e.g., RGB-D images), and the abstraction is reached by exploiting image segmentation and the Taskonomy model bank. The learning of the Abstract Model is accomplished by executing actions, observing the reached state, and updating the Abstract Model with the acquired information. The learned models are memorized by the agent, and they are reused whenever it recognizes to be in an environment that corresponds to the stored model. We investigate the effectiveness of the proposed approach for the Object Goal Navigation task, relying on public benchmarks. Our results show that the reuse of learned Abstract Models can boost performance on Object Goal Navigation.

Events are structured entities involving different components (e.g, the participants, their roles etc.) and their relations. Structured events are typically defined in terms of (a subset of) simpler, atomic events and a set of temporal relation between them. Temporal Event Detection (TED) is the task of detecting structured and atomic events within data streams, most often text or video sequences, and has numerous applications, from video surveillance to sports analytics. Existing deep learning approaches solve TED task by implicitly learning the temporal correlations among events from data. As consequence, these approaches often fail in ensuring a consistent prediction in terms of the relationship between structured and atomic events. On the other hand, neuro-symbolic approaches have shown their capability to constrain the output of the neural networks to be consistent with respect to the background knowledge of the domain. In this paper, we propose a neuro-symbolic approach for TED in a real world scenario involving sports activities. We show how by incorporating simple knowledge involving the relative order of atomic events and constraints on their duration, the approach substantially outperforms a fully neural solution in terms of recognition accuracy, when little or even no supervision is available on the atomic events.

Abstract Reasoning on defeasible knowledge is a topic of interest in the area of description logics, as it is related to the need of representing exceptional instances in knowledge bases. In this direction, in our previous works we presented a framework for representing (contextualized) OWL RL knowledge bases with a notion of justified exceptions on defeasible axioms: reasoning in such framework is realized by a translation into ASP programs. The resulting reasoning process for OWL RL, however, introduces a complex encoding in order to capture reasoning on the negative information needed for reasoning on exceptions. In this paper, we apply the justified exception approach to knowledge bases in , that is, the language underlying OWL QL. We provide a definition for knowledge bases with defeasible axioms and study their semantic and computational properties. In particular, we study the effects of exceptions over unnamed individuals. The limited form of axioms allows us to formulate a simpler ASP encoding, where reasoning on negative information is managed by direct rules. The resulting materialization method gives rise to a complete reasoning procedure for instance checking in with defeasible axioms.1

We propose an approach to learn an extensional representation of a discrete deterministic planning domain from observations in a continuous space navigated by the agent actions. This is achieved through the use of a perception function providing the likelihood of a real-value observation being in a given state of the planning domain after executing an action. The agent learns an extensional representation of the domain (the set of states, the transitions from states to states caused by actions) and the perception function on-line, while it acts for accomplishing its task. In order to provide a practical approach that can scale up to large state spaces, a “draft” intensional (PDDL-based) model of the planning domain is used to guide the exploration of the environment and learn the states and state transitions. The proposed approach uses a novel algorithm to (i) construct the extensional representation of the domain by interleaving symbolic planning in the PDDL intensional representation and search in the state transition graph of the extensional representation; (ii) incrementally refine the intensional representation taking into account information about the actions that the agent cannot execute. An experimental analysis shows that the novel approach can scale up to large state spaces, thus overcoming the limits in scalability of the previous work.

The automated learning of action models is widely recognised as a key and compelling challenge to address the difficulties of the manual specification of planning domains. Most state-of-the-art methods perform this learning offline from an input set of plan traces generated by the execution of (successful) plans. However, how to generate informative plan traces for learning action models is still an open issue. Moreover, plan traces might not be available for a new environment. In this paper, we propose an algorithm for learning action models online, incrementally during the execution of plans. Such plans are generated to achieve goals that the algorithm decides online in order to obtain informative plan traces and reach states from which useful information can be learned. We show some fundamental theoretical properties of the algorithm, and we experimentally evaluate the online learning of the action models over a large set of IPC domains.

Complex activity recognition can benefit from understanding the steps that compose them. Current datasets, however, are annotated with one label only, hindering research in this direction. In this paper, we describe a new dataset for sensor-based activity recognition featuring macro and micro activities in a cooking scenario. Three sensing systems measured simultaneously, namely a motion capture system, tracking 25 points on the body; two smartphone accelerometers, one on the hip and the other one on the forearm; and two smartwatches one on each wrist. The dataset is labeled for both the recipes (macro activities) and the steps (micro activities). We summarize the results of a baseline classification using traditional activity recognition pipelines. The dataset is designed to be easily used to test and develop activity recognition approaches.

The problem of reasoning with context dependent knowledge has recently gained interest in the area of description logic-based knowledge bases (KBs). Among the several proposals, we consider the Contextualized Knowledge Repository (CKR) framework. The CKR model has been recently extended with the capability of reasoning with global (context independent) defeasible axioms that can be overridden by local (context specific) knowledge. In CKR applications it is often useful to reason over a hierarchical organization of contexts. We highlight here our recent efforts on extending the CKR framework to allow for the representation of exception handling in the inheritance of knowledge across local contexts. We first concentrated on a limitation to a particular kind of context organization, i.e., ranked hierarchies, which allows us to simplify the definition of reasoning procedures. We then further generalized the proposal to extend the reasoning on exception handling over general contextual hierarchies. In this paper we summarize the basic definitions for simple CKRs with Justifiable Exceptions, the emerging computational properties, and the ASP-based reasoning procedures that we developed. Moreover, we highlight the open challenges in generalizing the approach and our future directions.

"A picture is worth a thousand words", the adage reads. However, pictures cannot replace words in terms of their ability to efficiently convey clear (mostly) unambiguous and concise knowledge. Images and text, indeed, reveal different and complementary information that, if combined, result in more information than the sum of that contained in the single media. The combination of visual and textual information can be obtained by linking the entities mentioned in the text with those shown in the pictures. To further integrate this with agent background knowledge, an additional step is necessary. That is, either finding the entities in the agent knowledge base that correspond to those mentioned in the text or shown in the picture or, extending the knowledge base with the newly discovered entities. We call this complex task Visual-Textual-Knowledge Entity Linking (VTKEL). In this paper, we precisely define the VTKEL task and present two datasets composed of 1k and 30k pictures, annotated with visual and textual entities and linked to the YAGO ontology. Successively, we develop the first unsupervised algorithm for the solution of VTKEL task. The evaluation of the algorithm shows promising results on both 1k and 30k VTKEL datasets.

Semantic Image Interpretation is the task of extracting a structured semantic description from images. This requires the detection of visual relationships: triples 〈subject, relation, object〉 describing a semantic relation between a subject and an object. A pure supervised approach to visual relationship detection requires a complete and balanced training set for all the possible combinations of 〈subject, relation, object〉. However, such training sets are not available and would require a prohibitive human effort. This implies the ability of predicting triples which do not appear in the training set. This problem is called zero-shot learning. State-of-the-art approaches to zero-shot learning exploit similarities among relationships in the training set or external linguistic knowledge. In this paper, we perform zero-shot learning by using Logic Tensor Networks, a novel Statistical Relational Learning framework that exploits both the similarities with other seen relationships and background knowledge, expressed with logical constraints between subjects, relations and objects. The experiments on the Visual Relationship Dataset show that the use of logical constraints outperforms the current methods. This implies that background knowledge can be used to alleviate the incompleteness of training sets.

The Contextualized Knowledge Repository (CKR) framework was conceived as a logic-based approach for representing context dependent knowledge, which is a well-known area of study in AI. The framework has a two-layer structure with a global context that contains context-independent knowledge and meta-information about the contexts, and a set of local contexts with specific knowledge bases. In many practical cases, it is desirable that inherited global knowledge can be "overridden" at the local level. In order to address this need, we present an extension of CKR with global defeasible axioms: these axioms locally apply to (tuples of) individuals unless an exception for overriding exists; such an exception, however, requires a justification that is provable from the knowledge base. We formalize this intuition and study its semantic and computational properties. Furthermore, we present a translation of extended CKRs to datalog programs under the answer set (i.e., stable) semantics and we present an implementation prototype. Our work adds to the body of results on using deductive database technology in these areas, and provides an expressive formalism for exception handling by overriding.

Semantic Image Interpretation (SII) is the task of extracting structured semantic descriptions from images. It is widely agreed that the combined use of visual data and background knowledge is of great importance for SII. Recently, Statistical Relational Learning (SRL) approaches have been developed for reasoning under uncertainty and learning in the presence of data and rich knowledge. Logic Tensor Networks (LTNs) are a SRL framework which integrates neural networks with first-order fuzzy logic to allow (i) efficient learning from noisy data in the presence of logical constraints, and (ii) reasoning with logical formulas describing general properties of the data. In this paper, we develop and apply LTNs to two of the main tasks of SII, namely, the classification of an image's bounding boxes and the detection of the relevant part-of relations between objects. To the best of our knowledge, this is the first successful application of SRL to such SII tasks. The proposed approach is evaluated on a standard image processing benchmark. Experiments show that background knowledge in the form of logical constraints can improve the performance of purely data-driven approaches, including the state-of-the-art Fast Region-based Convolutional Neural Networks (Fast R-CNN). Moreover, we show that the use of logical background knowledge adds robustness to the learning system when errors are present in the labels of the training data.

Abstract Environmental and meteorological conditions are of utmost importance for the population, as they are strongly related to the quality of life. Citizens are increasingly aware of this importance. This awareness results in an increasing demand for environmental information tailored to their specific needs and background. We present an environmental information platform that supports submission of user queries related to environmental conditions and orchestrates results from complementary services to generate personalized suggestions. The system discovers and processes reliable data in the Web in order to convert them into knowledge. At runtime, this information is transferred into an ontology‐structured knowledge base, from which then information relevant to the specific user is deduced and communicated in the language of their preference. The platform is demonstrated with real world use cases in the south area of Finland, showing the impact it can have on the quality of everyday life.

Although the quantity of structured information on the Web and within organizations is increasing, the majority of information remains available only in unstructured form. While different in form, both unstructured and structured information sources provide information about entities in the world and their properties and relations; still, frameworks for their seamless integration have not been deeply investigated. In this paper the authors describe the KnowledgeStore, a scalable, fault-tolerant, and Semantic Web grounded open-source storage system for interlinking structured and unstructured data. They present the concept, design, function and implementation of the system, and report on its concrete usage in three application scenarios within the NewsReader EU project, where it stores and supports the querying of millions of news articles interlinked with millions of RDF triples extracted from text and imported from Linked Open Data sources. The authors report on data population and data retrieval performances of the system measured through a number of experiments, and they also discuss the practical issues and lessons learned from these experiences.

In this paper, we describe how we combine active and passive user input modes in clinical environments for knowledge discovery and knowledge acquisition towards decision support in clinical environments. Active input modes include digital pens, smartphones, and automatic handwriting recognition for a direct digitalisation of patient data. Passive input modes include sensors of the clinical environment and or mobile smartphones. This combination for knowledge acquisition and decision support (while using machine learning techniques) has not yet been explored in clinical environments and is of specific interest because it combines previously unconnected information sources for individualised treatments. The innovative aspect is a holistic view on individual patients based on ontologies, terminologies, and textual patient records whereby individual active and passive real-time patient data can be taken into account for improving clinical decision support.

As the amount of available linked data expand and the number of related applications increases, the management of aspects such as provenance and access control of such data begin to become an issue. Current approaches do not provide sufficient support for automatic reasoning over different metadata types and their possible interdependencies. MetaReasons is a framework that supports representation and automated reasoning over metadata in a single logical formalism. Different types of metadata, like data-provenance and accessibility-restrictions, are represented as distinct meta-theories and dependencies between metadata types are represented by rules between different meta-theories. In this paper we present the definition of the MetaReasons framework and two examples meta-theories for provenance and access control. Moreover, we propose a materialization calculus for forward reasoning on the two aspects.

In this paper we describe a formal ontological description of the Business Process Modelling Notation (BPMN), one of the most popular languages for business process modelling. The proposed ontology (the BPMN Ontology) provides a classification of all the elements of BPMN, together with the formal description of the attributes and conditions describing how the elements can be combined in a BPMN business process description. Using the classes and properties defined in the BPMN Ontology any BPMN diagram can be represented as an A-box (i.e., a set of instances and assertions on them) of the ontology: this allows the exploitation of ontological reasoning services such as consistency checking and query answering to investigate the compliance of a process with the BPMN Specification as well as other structural property of the process. The paper also presents the modelling process followed for the creation of the BPMN Ontology, and describes some application scenarios exploiting the BPMN Ontology.

The capability of dealing with context sensitive knowledge is recognized as a crucial aspect in the management of massive amounts of Semantic Web (SW) data. Contextual knowledge can be modelled either by adopting the primitives from RDF/OWL based SW languages or by extending such languages with new specific constructs for context representation. In this paper, we show the benefits of the context-based solution by comparing modelling and reasoning in the two approaches on the paradigmatic use case of FIFA World Cup. The comparison considers the three key aspects of engineering and exploiting knowledge: (i) simplicity and expressivity of the (formal) language; (ii) compactness of the representation; and (iii) efficiency of reasoning. As for (i), we show that the context-based language enables the construction of simpler and more intuitive models while the RDF/OWL "flat" model presents practical limitations in modelling cross-contextual knowledge. For (ii), we show that the contextualized model is more compact than the OWL based model. Finally for (iii), query answering in the context-based model outperforms in most of the cases performances on the flat model.

The pervasiveness of mobile phones creates an unprecedented opportunity for analyzing human dynamics with the help of the data they generate. This enables a novel human-driven approach for service creation in a variety of domains (e.g., healthcare, transportation, etc.) Telecom operators own and manage billions of mobile network events (Call Detailed Records - CDRs) per day: interpreting such a big stream of data needs a deep understanding of the events' context through the available background knowledge. We introduce an ontological and stochastic model (HRBModel) to interpret mobile human behavior using merged mobile network data and the geo-referenced background knowledge (e.g., OpenStreetMap, etc.) The model characterizes locations with human activities that can happen (with a given likelihood) there. This allows us to predicatively compile sets of tasks that people are likely to engage in under certain contextual conditions or to characterize exceptional events detected from anomalies in the CDR. An experimental evaluation of the approach is presented.

Enriching business process models with semantic annotations that are taken from an ontology has become a crucial need in service provisioning, integration and composition, and business processes management. We represent semantically annotated business processes as part of an Web ontology lanuage knowledge base that formalizes the business process structure, the business domain, a set of criteria that describe correct semantic annotations, and a set of constraints that describe requirements on the business process itself. In this paper, we show how the Semantic Web representation and reasoning techniques can be 1) exploited by our aspect-oriented approach to modularize exception-handling (as well as other crosscutting) mechanisms and 2) effectively applied to formalize and automatically verify constraints on the management of exceptional flows (as well as other relevant flows) in business processes. The benefits of the Semantic Web and the aspect-oriented technologies are illustrated in a case study, where exceptional flows are modularized separately and managed at the semantic level due to the proposed approach.

Abstract Semantic annotations are a way to provide a precise meaning to business process elements, which supports reasoning on properties and constraints. Among the obstacles preventing widespread adoption of semantic annotations are the technical skills required to manage the formalization of the semantics and the difficulty of reconciling the different viewpoints of different analysts working on the same business process. In this paper, we support business analysts in the collaborative annotation of business processes by means of a tool inspired to the Wiki pages model. Using this tool, analysts can concurrently work on process elements, ontology concepts, process annotation or constraint specification. The underlying formalism is not exposed in the Wiki pages, where natural language templates are used. Copyright © 2011 John Wiley & Sons, Ltd.

Systems based on statistical and machine learning methods have been shown to be extremely effective and scalable for the analysis of large amount of textual data. However, in the recent years, it becomes evident that one of the most important direction of improvement in natural language processing (NLP) tasks, like word sense disambiguation, coreference resolution, relation extraction, and other tasks related to knowledge extraction, is by exploiting semantics. While in the past, the unavailability of rich and complete semantic descriptions constituted a serious limitation of their applicability, nowadays, the Semantic Web made available a large amount of logically encoded information (e.g. ontologies, RDF(S)-data, linked data, etc.), which constitute a valuable source of semantics. However, web semantics cannot be easily plugged into machine learning systems. Therefore the objective of this paper is to define a reference methodology for combining semantics information available in the web under the form of logical theories, with statistical methods for NLP. The major problems that we have to solve to implement our methodology concern (i) the selection of the correct and minimal knowledge among the large amount available in the web, (ii) the representation of uncertain knowledge, and (iii) the resolution and the encoding of the rules that combine knowledge retrieved from Semantic Web sources with semantics in the text. In order to evaluate the appropriateness of our approach, we present an application of the methodology to the problem of intra-document coreference resolution, and we show by means of some experiments on the ACE 2005 dataset, how the injection of knowledge is correlated to the improvement of the performance of our approach on this tasks.

State of the art formalisms for distributed ontology integration provide ways to express semantic relations between homogeneous components of different ontologies; namely, they allow to map concepts into concepts, individuals into individuals, and properties into properties. However, the extensive usage of multiple distributed ontologies requires the capability for expressing different forms of mappings, which extend the semantic relations among homogeneous components studied so far. In recent papers extensions of the Distributed Description Logic (DDL) have been proposed to represent mappings between heterogeneous elements; i.e. mappings connecting concepts and relations. In this paper we investigate the computational properties of reasoning with mappings between homogeneous as well as heterogeneous elements in distributed ontologies, and an effective decision procedure for reasoning with multiple ontologies bridged with both forms of mappings.

In most web sites, web-based applications (such as web portals, e-marketplaces, search engines), and in the file systems of personal computers, a wide variety of schemas (such as taxonomies, directory trees, thesauri, Entity-Relationship schemas, RDF Schemas) are published which (i) convey a clear meaning to humans (e.g. help in the navigation of large collections of documents), but (ii) convey only a small fraction (if any) of their meaning to machines, as their intended meaning is not formally/explicitly represented. In this paper we present a general methodology for automatically eliciting and representing the intended meaning of these structures, and for making this meaning available in domains like information integration and interoperability, web service discovery and composition, peer-to-peer knowledge management, and semantic browsers. We also present an implementation (called CtxMatch2) of how such a method can be used for semantic interoperability.

We are working on a system for the optimised access and replication of data on a Data Grid. Our approach is based on the use of an economic model that includes the actors and the resources in the Grid. Optimisation is obtained via interaction of the actors in the model, whose goals are maximising the profits and minimising the costs of data resource management. In the system, local optimisation results in global optimisation through emergent marketplace behaviour. In this paper we give an overview of our model and present part of the complex economic reasoning required to support this desired marketplace interaction model.

We propose a framework, called OM pairs, for the formalization of metareasoning. OM pairs allow us to generate deductively pairs composed of an object theory and a metatheory related via a so called reflection principle. This is done by imposing, via appropriate reflection rules, the relation we want to hold between the object theory and the metatheory. In this paper we concentrate on the proof theory of OM pairs. We study them from various points of view: we compare the strength of the object theory and the metatheories generated by different combination of reflection rules; for each combination we characterize the object theory and metatheory, both axiomatically (when possible), and by means of fix‐point equations. Finally we present four important case studies.

OM pairs are our proposed framework for the formalization of metareasoning. OM pairs allow us to generate deductively the object theory and/or the metatheory. This is done by imposing, via appropriate reflection rules, the relation we want to hold between the object theory and the metatheory. In a previous paper we have studied the proof theoretic properties of OM pairs. In this paper we study their model theoretic properties, in particular we study the relation between the models of the metatheory and the object theory; and how to use these results to refine the previous analysis.

In order to perform effective communication, agents must be able to foresee the effects of their utterances on the addressee's mental state. In this paper we study the consequences of an utterance on the mental state of a hearer. Given an agent communication language with a STRIPS‐like semantics, we propose a set of criteria that allow the binding of the speaker's mental state to its uttering of a certain sentence. On the basis of these criteria, we give an abductive procedure that the hearer can adopt to partially recognize the speaker's mental state that led to a specific utterance.

The goal of this paper is to present a logical framework for the formalization of agents' mutual beliefs in a Multi Agent system. The approach is based on a combination of extensional specifications of beliefs and context-based (finite) presentation of the specifications by employing a particular class of Multi Context systems. The extensional specification provides a set-theoretic characterization of beliefs in terms of sets closed under certain conditions. Its finite presentation is provided by using as constructors inference rules inside a Multi Context system. The resulting framework allows for capturing many relevant cases of real (not omniscient) agents, which are very common in Multi Agent scenarios embedded in real world environments. In order to substantiate this claim, two Multi Agent scenarios are formally specified in detail in the specification framework. ©1999 John Wiley & Sons, Inc.

Dottorato di ricerca in ingegneria elettronica e informatica. 11. ciclo. Relatori M. Di Manzo e F. Giunchiglia