Luciano Serafini

AIJ Journal 2025 Journal Article

Lifted action models learning from partial traces

• Leonardo Lamanna
• Luciano Serafini
• Alessandro Saetti
• Alfonso Emilio Gerevini
• Paolo Traverso

For applying symbolic planning, there is the necessity of providing the specification of a symbolic action model, which is usually manually specified by a domain expert. However, such an encoding may be faulty due to either human errors or lack of domain knowledge. Therefore, learning the symbolic action model in an automated way has been widely adopted as an alternative to its manual specification. In this paper, we focus on the problem of learning action models offline, from an input set of partially observable plan traces. In particular, we propose an approach to: (i) augment the observability of a given plan trace by applying predefined logical rules; (ii) learn the preconditions and effects of each action in a plan trace from partial observations before and after the action execution. We formally prove that our approach learns action models with fundamental theoretical properties, not provided by other methods. We experimentally show that our approach outperforms a state-of-the-art method on a large set of existing benchmark domains. Furthermore, we compare the effectiveness of the learned action models for solving planning problems and show that the action models learned by our approach are much more effective w. r. t. a state-of-the-art method. 1

AIJ Journal 2025 Journal Article

Lifted inference beyond first-order logic

• Sagar Malhotra
• Davide Bizzaro
• Luciano Serafini

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 ($\mathrm{C^2}$) is domain-liftable. However, many properties of real-world data, like acyclicity in citation networks and connectivity in social networks, cannot be modeled in $\mathrm{C^2}$, or first order logic in general. In this work, we expand the domain liftability of $\mathrm{C^2}$ with multiple such properties. We show that any $\mathrm{C^2}$ 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.

ICAPS Conference 2024 Conference Paper

Action Model Learning from Noisy Traces: a Probabilistic Approach

• Leonardo Lamanna 0001
• Luciano Serafini

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.

ECAI Conference 2024 Conference Paper

IFH: A Diffusion Framework for Flexible Design of Graph Generative Models

• Samuel Cognolato
• Alessandro Sperduti
• Luciano Serafini

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.

NeSy Conference 2024 Conference Paper

Simple and Effective Transfer Learning for Neuro-Symbolic Integration

• Alessandro Daniele
• Tommaso Campari
• Sagar Malhotra
• Luciano Serafini

Abstract Deep Learning (DL) techniques have achieved remarkable successes in recent years. However, their ability to generalize and execute reasoning tasks remains a challenge. A potential solution to this issue is Neuro-Symbolic Integration (NeSy), where neural approaches are combined with symbolic reasoning. Most of these methods exploit a neural network to map perceptions to symbols and a logical reasoner to predict the output of the downstream task. These methods exhibit superior generalization capacity compared to fully neural architectures. However, they suffer from several issues, including slow convergence, learning difficulties with complex perception tasks, and convergence to local minima. This paper proposes a simple yet effective method to ameliorate these problems. The key idea involves pretraining a neural model on the downstream task. Then, a NeSy model is trained on the same task via transfer learning, where the weights of the perceptual part are injected from the pretrained network. The key observation of our work is that the neural network fails to generalize only at the level of the symbolic part while being perfectly capable of learning the mapping from perceptions to symbols. We have tested our training strategy on various SOTA NeSy methods and datasets, demonstrating consistent improvements in the aforementioned problems.

IJCAI Conference 2023 Conference Paper

Deep Symbolic Learning: Discovering Symbols and Rules from Perceptions

• Alessandro Daniele
• Tommaso Campari
• Sagar Malhotra
• Luciano Serafini

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.

NeSy Conference 2023 Conference Paper

Deep Symbolic Learning: Discovering Symbols and Rules from Perceptions

• Alessandro Daniele
• Tommaso Campari
• Sagar Malhotra
• Luciano Serafini

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 Symbolic 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 learns simultaneously 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.

IJCAI Conference 2023 Conference Paper

Learning to Act for Perceiving in Partially Unknown Environments

• Leonardo Lamanna
• Mohamadreza Faridghasemnia
• Alfonso Gerevini
• Alessandro Saetti
• Alessandro Saffiotti
• Luciano Serafini
• Paolo Traverso

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.

AAAI Conference 2023 Conference Paper

Planning for Learning Object Properties

• Leonardo Lamanna
• Luciano Serafini
• Mohamadreza Faridghasemnia
• Alessandro Saffiotti
• Alessandro Saetti
• Alfonso Gerevini
• Paolo Traverso

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.

TIME Conference 2022 Conference Paper

A Neuro-Symbolic Approach for Real-World Event Recognition from Weak Supervision

• Gianluca Apriceno
• Andrea Passerini
• Luciano Serafini

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.

AIJ Journal 2022 Journal Article

Logic Tensor Networks

• Samy Badreddine
• Artur d'Avila Garcez
• Luciano Serafini
• Michael Spranger

Attempts at combining logic and neural networks into neurosymbolic approaches have been on the increase in recent years. In a neurosymbolic system, symbolic knowledge assists deep learning, which typically uses a sub-symbolic distributed representation, to learn and reason at a higher level of abstraction. We present Logic Tensor Networks (LTN), a neurosymbolic framework that supports querying, learning and reasoning with both rich data and abstract knowledge about the world. LTN introduces a fully differentiable logical language, called Real Logic, whereby the elements of a first-order logic signature are grounded onto data using neural computational graphs and first-order fuzzy logic semantics. We show that LTN provides a uniform language to represent and compute efficiently many of the most important AI tasks such as multi-label classification, relational learning, data clustering, semi-supervised learning, regression, embedding learning and query answering. We implement and illustrate each of the above tasks with several simple explanatory examples using TensorFlow 2. The results indicate that LTN can be a general and powerful framework for neurosymbolic AI.

NeSy Conference 2022 Conference Paper

Logic Tensor Networks for Top-N Recommendation

• Tommaso Carraro
• Alessandro Daniele
• Fabio Aiolli
• Luciano Serafini

Despite being studied for more than twenty years, state-of-the-art recommendation systems still suffer from important drawbacks which limit their usage in real-world scenarios. Among the well-known issues of recommender systems, there are data sparsity and the cold-start problem. These limitations can be addressed by providing some background knowledge to the model to compensate for the scarcity of data. Following this intuition, we propose to use Logic Tensor Networks (LTNs) to tackle the top-n item recommendation problem. In particular, we show how LTNs can be used to easily and effectively inject commonsense recommendation knowledge inside a recommender system. We evaluate our method on MindReader, a knowledge graph-based movie recommendation dataset containing plentiful side information. In particular, we perform an experiment to show how the benefits of the knowledge increase with the sparsity of the dataset. Eventually, a comparison with a standard Matrix Factorization approach reveals that our model is able to reach and, in many cases, outperform state-of-the-art performance.

KR Conference 2022 Conference Paper

Online Grounding of Symbolic Planning Domains in Unknown Environments

• Leonardo Lamanna
• Luciano Serafini
• Alessandro Saetti
• Alfonso Gerevini
• Paolo Traverso

If a robotic agent wants to exploit symbolic planning techniques to achieve some goal, it must be able to properly ground an abstract planning domain in the environment in which it operates. However, if the environment is initially unknown by the agent, the agent needs to explore it and discover the salient aspects of the environment necessary to reach its goals. Namely, the agent has to discover: (i) the objects present in the environment, (ii) the properties of these objects and their relations, and finally (iii) how abstract actions can be successfully executed. The paper proposes a framework that aims to accomplish the aforementioned perspective for an agent that perceives the environment partially and subjectively, through real value sensors (e. g. , GPS, and on-board camera) and can operate in the environment through low level actuators (e. g. , move forward of 20 cm). We evaluate the proposed architecture in photo-realistic simulated environments, where the sensors are RGB-D on-board camera, GPS and compass, and low level actions include movements, grasping/releasing objects, and manipulating objects. The agent is placed in an unknown environment and asked to find objects of a certain type, place an object on top of another, close or open an object of a certain type. We compare our approach with a state of the art method on object goal navigation based on reinforcement learning, showing better performances.

AAAI Conference 2022 Conference Paper

Weighted Model Counting in FO2 with Cardinality Constraints and Counting Quantifiers: A Closed Form Formula

• Sagar Malhotra
• Luciano Serafini

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.

TIME Conference 2021 Conference Paper

A Neuro-Symbolic Approach to Structured Event Recognition

• Gianluca Apriceno
• Andrea Passerini
• Luciano Serafini

Events are structured entities with multiple components: the event type, the participants with their roles, the outcome, the sub-events etc. A fully end-to-end approach for event recognition from raw data sequence, therefore, should also solve a number of simpler tasks like recognizing the objects involved in the events and their roles, the outcome of the events as well as the sub-events. Ontological knowledge about event structure, specified in logic languages, could be very useful to solve the aforementioned challenges. However, the majority of successful approaches in event recognition from raw data are based on purely neural approaches (mainly recurrent neural networks), with limited, if any, support for background knowledge. These approaches typically require large training sets with detailed annotations at the different levels in which recognition can be decomposed (e. g. , video annotated with object bounding boxes, object roles, events and sub-events). In this paper, we propose a neuro-symbolic approach for structured event recognition from raw data that uses "shallow" annotation on the high-level events and exploits background knowledge to propagate this supervision to simpler tasks such as object classification. We develop a prototype of the approach and compare it with a purely neural solution based on recurrent neural networks, showing the higher capability of solving both the event recognition task and the simpler task of object classification, as well as the ability to generalize to events with unseen outcomes.

AAAI Conference 2021 Conference Paper

On-line Learning of Planning Domains from Sensor Data in PAL: Scaling up to Large State Spaces

• Leonardo Lamanna
• Alfonso Emilio Gerevini
• Alessandro Saetti
• Luciano Serafini
• Paolo Traverso

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 statetransition 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 current approaches.

IJCAI Conference 2021 Conference Paper

Online Learning of Action Models for PDDL Planning

• Leonardo Lamanna
• Alessandro Saetti
• Luciano Serafini
• Alfonso Gerevini
• Paolo Traverso

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.

ECAI Conference 2020 Conference Paper

Reasoning with Justifiable Exceptions in Contextual Hierarchies

• Loris Bozzato
• Luciano Serafini
• Thomas Eiter

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.

ECAI Conference 2020 Conference Paper

VT-LINKER: Visual-Textual-Knowledge Entity Linker

• Shahi Dost
• Luciano Serafini
• Marco Rospocher
• Lamberto Ballan
• Alessandro Sperduti

“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.

FLAP Journal 2019 Journal Article

Neural-symbolic Computing: An Effective Methodology for Principled Integration of Machine Learning and Reasoning.

• Artur S. d'Avila Garcez
• Marco Gori
• Luís C. Lamb
• Luciano Serafini
• Michael Spranger
• Son N. Tran

AIJ Journal 2018 Journal Article

Enhancing context knowledge repositories with justifiable exceptions

• Loris Bozzato
• Thomas Eiter
• Luciano Serafini

Dealing with context dependent knowledge is a well-known area of study that roots in John McCarthy's seminal work. More recently, the Contextualized Knowledge Repository (CKR) framework has been conceived as a logic-based approach in which knowledge bases have a two layered structure, modeled by a global context and a set of local contexts. The global context not only contains the meta-knowledge defining the properties of local contexts, but also holds the global (context independent) object knowledge that is shared by all of the local contexts. In many practical cases, however, it is desirable to leave the possibility to “override” the global object knowledge at the local level: in other words, it is interesting to recognize the pieces of knowledge that can admit exceptional instances in the local contexts that do not need to satisfy the general axiom. To address this need, we present in this paper an extension of CKR in which defeasible axioms can be included in the global context. The latter are verified in the local contexts only for the instances for which no exception to overriding exists, where exceptions require a justification in terms of facts that are provable from the knowledge base. We formally define this semantics and study some semantic and computational properties, where we characterize the complexity of the major reasoning tasks, among them satisfiability testing, instance checking, and conjunctive query answering. Furthermore, we present a translation of extended CKRs with knowledge bases in the Description Logic SROIQ -RL under the novel semantics to datalog programs under the stable model (answer set) semantics. We also present an implementation prototype and examine its scalability with respect to the size of the input CKR and the amount (level) of defeasibility in experiments. Finally, we compare our representation approach with some major formalisms for expressing defeasible knowledge in Description Logics and contextual knowledge representation. Our work adds to the body of results on using deductive database technology such as SQL and datalog in these areas, and provides an expressive formalism (in terms of intrinsic complexity) for exception handling by overriding.

IJCAI Conference 2018 Conference Paper

Enhancing Context Knowledge Repositories with Justifiable Exceptions (Extended Abstract)

• Loris Bozzato
• Thomas Eiter
• Luciano Serafini

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.

KR Conference 2018 Conference Paper

Reasoning with Justifiable Exceptions in Contextual Hierarchies

• Loris Bozzato
• Luciano Serafini
• Thomas Eiter

The problem of representing and reasoning with context dependent knowledge has been of certain interest since the beginning of AI. Among the available solutions, we consider the Contextualized Knowledge Repository (CKR) framework. In CKR applications it is often useful to reason over a hierarchical organization of contexts: however, the CKR model is not able to represent exception handling in the inheritance of knowledge across contexts. In this paper we develop a proposal, based on a recent principle for exception handling for inheritance in description logics, that allows CKRs with context dependent defeasible axioms which can be overridden by more specific local knowledge. We provide an alternative semantics for a core (simple) version of CKR that copes with contextual defeasible axioms, and we define a datalog translation generating programs that are complete w. r. t. instance checking under the proposed semantics in the case of ranked contextual hierarchies.

AIJ Journal 2017 Journal Article

Distributed First Order Logic

• Chiara Ghidini
• Luciano Serafini

Distributed First Order Logic (DFOL) has been introduced more than ten years ago with the purpose of formalising distributed knowledge-based systems, where knowledge about heterogeneous domains is scattered into a set of interconnected modules. DFOL formalises the knowledge contained in each module by means of first-order theories, and the interconnections between modules by means of special inference rules called bridge rules. Despite their restricted form in the original DFOL formulation, bridge rules have influenced several works in the areas of heterogeneous knowledge integration, modular knowledge representation, and schema/ontology matching. This, in turn, has fostered extensions and modifications of the original DFOL that have never been systematically described and published. This paper tackles the lack of a comprehensive description of DFOL by providing a systematic account of a completely revised and extended version of the logic, together with a sound and complete axiomatisation of a general form of bridge rules based on Natural Deduction. The resulting DFOL framework is then proposed as a clear formal tool for the representation of and reasoning about distributed knowledge and bridge rules.

IJCAI Conference 2017 Conference Paper

Logic Tensor Networks for Semantic Image Interpretation

• Ivan Donadello
• Luciano Serafini
• Artur d'Avila Garcez

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.

NeSy Conference 2016 Conference Paper

Logic Tensor Networks: Deep Learning and Logical Reasoning from Data and Knowledge

• Luciano Serafini
• Artur S. d'Avila Garcez

We propose Logic Tensor Networks: a uniform framework for integrating automatic learning and reasoning. A logic formalism called Real Logic is defined on a first-order language whereby formulas have truth-value in the interval [0, 1] and semantics defined concretely on the domain of real numbers. Logical constants are interpreted as feature vectors of real numbers. Real Logic promotes a well-founded integration of deductive reasoning on a knowledge-base and efficient data-driven relational machine learning. We show how Real Logic can be implemented in deep Tensor Neural Networks with the use of Google’s TEN- SORFLOW TM primitives. The paper concludes with experiments applying Logic Tensor Networks on a simple but representative example of knowledge completion.

IJCAI Conference 2015 Conference Paper

Bootstrapping Domain Ontologies from Wikipedia: A Uniform Approach

• Daniil Mirylenka
• Andrea Passerini
• Luciano Serafini

Building ontologies is a difficult task requiring skills in logics and ontological analysis. Domain experts usually reach as far as organizing a set of concepts into a hierarchy in which the semantics of the relations is under-specified. The categorization of Wikipedia is a huge concept hierarchy of this form, covering a broad range of areas. We propose an automatic method for bootstrapping domain ontologies from the categories of Wikipedia. The method first selects a subset of concepts that are relevant for a given domain. The relevant concepts are subsequently split into classes and individuals, and, finally, the relations between the concepts are classified into subclass of, instance of, part of, and generic related to. We evaluate our method by generating ontology skeletons for the domains of Computing and Music. The quality of the generated ontologies has been measured against manually built ground truth datasets of several hundred nodes.

ECAI Conference 2014 Conference Paper

Combining Reasoning on Semantic Web Metadata

• Loris Bozzato
• Luciano Serafini

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.

ECAI Conference 2010 Conference Paper

Using Background Knowledge to Support Coreference Resolution

• Volha Bryl
• Claudio Giuliano
• Luciano Serafini
• Kateryna Tymoshenko

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.

IJCAI Conference 2007 Conference Paper

• Gerhard Brewka
• Floris Roelofsen
• Luciano Serafini

In this paper we introduce a multi-context variant of Reiter's default logic. The logic provides a syntactical counterpart of Roelofsen and Serafini's information chain approach (IJCAI-05), yet has several advantages: it is closer to standard ways of representing nonmonotonic inference and a number of results from that area come for free; it is closer to implementation, in particular the restriction to logic programming gives us a computationally attractive framework; and it allows us to handle a problem with the information chain approach related to skeptical reasoning.

AAMAS Conference 2006 Conference Paper

Verifying space and time requirements for resource-bounded agents

• Natasha Alechina
• Piergiorgio Bertoli
• Chiara Ghidini
• Mark Jago
• Brian Logan
• Luciano Serafini

IJCAI Conference 2005 Conference Paper

A Formal Investigation of Mapping Language for Terminological Knowledge

• Luciano Serafini
• Heiner Stuckenschmidt
• Holger

IJCAI Conference 2005 Conference Paper

Aspects of Distributed and Modular Ontology Reasoning

• Luciano Serafini
• Alex Borgida
• Andrei

We investigate a formalism for reasoning with multiple local ontologies, connected by directional semantic mappings. We propose: (1) a relatively small change of semantics which localizes inconsistency (thereby making unnecessary global satisfiability checks), and preserves directionality of “knowledge import”; (2) a characterization of inferences using a fixed-point operator, which can form the basis of a cache-based implementation for local reasoners; (3) a truly distributed tableaux algorithm for cases when the local reasoners use subsets of SHIQ. Throughout, we indicate the applicability of the results to several recent proposals for knowledge representation and reasoning that support modularity, scalability and distributed reasoning.

AIJ Journal 2004 Journal Article

Comparing formal theories of context in AI

• Luciano Serafini
• Paolo Bouquet

The problem of context has a long tradition in different areas of artificial intelligence (AI). However, formalizing context has been widely discussed only since the late 80s, when J. McCarthy argued that formalizing context was a crucial step toward the solution of the problem of generality. Since then, two main formalizations have been proposed in AI: Propositional Logic of Context (PLC) and Local Models Semantics/MultiContext Systems (LMS/MCS). In this paper, we propose the first in depth comparison between these two formalizations, both from a technical and a conceptual point of view. The main technical result of this paper is the formal proof of the following facts: (i) PLC can be embedded into a particular class of MCS, called MPLC; (ii) MCS/LMS cannot be embedded in PLC using only lifting axioms to encode bridge rules, and (iii) under some important restrictions (including the hypothesis that each context has finite and homogeneous propositional languages), MCS/LMS can be embedded in PLC with generic axioms. The last part of the paper contains a comparison of the epistemological adequacy of PLC and MCS/LMS for the representation of the most important issues about contexts.

AAAI Conference 2004 Conference Paper

Complexity of Contextual Reasoning

• Floris Roelofsen
• Luciano Serafini

This paper delineates the computational complexity of propositional multi-context systems. We establish NP-membership by translating multi-context systems into bounded modal Kn, and obtain more refined complexity results by achieving the so-called bounded model property: the number of local models needed to satisfy a set of formulas Φ in a multi-context system MS is bounded by the number of contexts addressed by Φ plus the number of bridge rules in MS. Exploiting this property of multi-context systems, we are able to encode contextual satisfiability into purely propositional satisfiability, providing for the implementation of contextual reasoners based on already existing specialized SAT solvers. Finally, we apply our results to improve complexity bounds for McCarthy’s propositional logic of context – we show that satisfiability in this framework can be settled in nondeterministic polynomial time O(|ϕ|2 ).

ECAI Conference 2004 Conference Paper

Many Hands Make Light Work: Localized Satisfiability for Multi-Context Systems

• Floris Roelofsen
• Luciano Serafini
• Alessandro Cimatti

KR Conference 2004 Conference Paper

Satisfiability for propositional contexts

• Floris Roelofsen
• Luciano Serafini

We propose a sound and complete satisfiability algorithm for propositional multi-context systems. In essence, the algorithm is a distribution policy built on top of local reasoning procedures, one for each context, which can be implemented by (a diversity of) customized state-of-the-art SAT solvers. The foremost intuition that has motivated our algorithm, and the very potential strength of contextual reasoning, is that of keeping reasoning as local as possible. In doing so, we improve on earlier established complexity results by Massacci. Moreover, our approach could be applied to enhance recent proposals by Amir and Mcilraith towards a new partition-based reasoning paradigm; particularly, our formalism allows for a more expressive description of interpartition relations, and we provide an algorithm that is explicitly designed to deal with this expressiveness.

KER Journal 2003 Journal Article

Context matching for electronic marketplaces: a case study

• MATTEO BONIFACIO
• ANTONIA DONÀ
• ALESSANDRA MOLANI
• Luciano Serafini

Matching algorithms automatically discover semantic relations between two autonomously developed conceptual representations of two overlapping domains. Typical examples of such conceptualisations are electronic market catalogues (e.g., unspsc and e C l @ ss ) and Web directories (e.g., google and yahoo ). The objective of this paper is the description of a use case in which the matching algorithm C tx M atch, developed at ITC-IRST and the University of Trento, has been used to re-classify into the Universal Standard Products and Services Classification ( unspsc ) the catalogue of office equipment and accessories used by a worldwide telecommunication company to classify its suppliers. On the basis of this experience we are envisaging new applications of the algorithm in the area of demand aggregation. We conclude the paper by briefly describing a future application in this area.

KR Conference 2002 Conference Paper

Updating Contexts

• Antonia Dona`
• Luciano Serafini

AIJ Journal 1994 Journal Article

Multilanguage hierarchical logics, or: How we can do without modal logics

• Fausto Giunchiglia
• Luciano Serafini

MultiLanguage systems (ML systems) are formal systems allowing the use of multiple distinct logical languages. In this paper we introduce a class of ML systems which use a hierarchy of first-order languages, each language containing names for the language below, and propose them as an alternative to modal logics. The motivations of our proposal are technical, epistemological, and implementational. From a technical point of view, we prove, among other things, that the set of theorems of the most common modal logics can be embedded (under the obvious bijective mapping between a modal and a first-order language) into that of the corresponding ML systems. Moreover, we show that ML systems have properties not holding for modal logics and argue that these properties are justified by our intuitions. This claim is motivated by the study of how ML systems can be used in the representation of beliefs (more generally, propositional attitudes) and provability, two areas where modal logics have been extensively used. Finally, from an implementation point of view, we argue that ML systems resemble closely the current practice in the computer representation of propositional attitudes and metatheoretic theorem proving.

IJCAI Conference 1993 Conference Paper

Non-omniscient belief as context-based reasoning

• Fausto Giunchiglia
• Luciano Serafini
• Enrico Giunchiglia
• Marcello Frixione