Search Results for author: Luciano Serafini

Found 26 papers, 4 papers with code

Online Grounding of PDDL Domains by Acting and Sensing in Unknown Environments

no code implementations18 Dec 2021 Leonardo Lamanna, Luciano Serafini, Alessandro Saetti, Alfonso Gerevini, Paolo Traverso

To effectively use an abstract (PDDL) planning domain to achieve goals in an unknown environment, an agent must instantiate such a domain with the objects of the environment and their properties.

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

no code implementations12 Oct 2021 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.

A formalisation of BPMN in Description Logics

no code implementations22 Sep 2021 Chiara Ghidini, Marco Rospocher, Luciano Serafini

In this paper we present a textual description, in terms of Description Logics, of the BPMN Ontology, which provides a clear semantic formalisation of the structural components of the Business Process Modelling Notation (BPMN), based on the latest stable BPMN specifications from OMG [BPMN Version 1. 1 -- January 2008].

A Better Loss for Visual-Textual Grounding

no code implementations11 Aug 2021 Davide Rigoni, Luciano Serafini, Alessandro Sperduti

Given a textual phrase and an image, the visual grounding problem is defined as the task of locating the content of the image referenced by the sentence.

Visual Grounding

Reasoning on $\textit{DL-Lite}_{\cal R}$ with Defeasibility in ASP

no code implementations28 Jun 2021 Loris Bozzato, Thomas Eiter, Luciano Serafini

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.

Logic Tensor Networks

1 code implementation25 Dec 2020 Samy Badreddine, Artur d'Avila Garcez, Luciano Serafini, Michael Spranger

In this paper, we present Logic Tensor Networks (LTN), a neurosymbolic formalism and computational model that supports learning and reasoning through the introduction of a many-valued, end-to-end differentiable first-order logic called Real Logic as a representation language for deep learning.

Multi-Label Classification Relational Reasoning +1

Weighted Model Counting in the two variable fragment with Cardinality Constraints: A Closed Form Formula

no code implementations25 Sep 2020 Sagar Malhotra, Luciano Serafini

We introduce the concept of lifted interpretations as a tool for formulating polynomials for WFOMC.

Neural Networks Enhancement with Logical Knowledge

1 code implementation13 Sep 2020 Alessandro Daniele, Luciano Serafini

In the recent past, there has been a growing interest in Neural-Symbolic Integration frameworks, i. e., hybrid systems that integrate connectionist and symbolic approaches to obtain the best of both worlds.

Multi-Label Classification

Exploiting Scene-specific Features for Object Goal Navigation

no code implementations21 Aug 2020 Tommaso Campari, Paolo Eccher, Luciano Serafini, Lamberto Ballan

We study this question in the context of Object Navigation, a problem in which an agent has to reach an object of a specific class while moving in a complex domestic environment.

Visual Navigation

Compensating Supervision Incompleteness with Prior Knowledge in Semantic Image Interpretation

2 code implementations1 Oct 2019 Ivan Donadello, Luciano Serafini

This requires the detection of visual relationships: triples (subject, relation, object) describing a semantic relation between a subject and an object.

Relational Reasoning Tensor Networks +2

A Note on Reasoning on $\textit{DL-Lite}_{\cal R}$ with Defeasibility

no code implementations22 May 2019 Loris Bozzato, Thomas Eiter, Luciano Serafini

Representation of defeasible information is of interest in description logics, as it is related to the need of accommodating exceptional instances in knowledge bases.


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

no code implementations15 May 2019 Artur d'Avila Garcez, Marco Gori, Luis C. Lamb, Luciano Serafini, Michael Spranger, Son N. Tran

In spite of the recent impact of AI, several works have identified the need for principled knowledge representation and reasoning mechanisms integrated with deep learning-based systems to provide sound and explainable models for such systems.

Incremental learning abstract discrete planning domains and mappings to continuous perceptions

no code implementations16 Oct 2018 Luciano Serafini, Paolo Traverso

Most of the works on planning and learning, e. g., planning by (model based) reinforcement learning, are based on two main assumptions: (i) the set of states of the planning domain is fixed; (ii) the mapping between the observations from the real word and the states is implicitly assumed or learned offline, and it is not part of the planning domain.

Incremental Learning Model-based Reinforcement Learning

Reasoning with Justifiable Exceptions in Contextual Hierarchies (Appendix)

no code implementations6 Aug 2018 Loris Bozzato, Luciano Serafini, Thomas Eiter

This paper is an appendix to the paper "Reasoning with Justifiable Exceptions in Contextual Hierarchies" by Bozzato, Serafini and Eiter, 2018.


Logic Tensor Networks for Semantic Image Interpretation

no code implementations24 May 2017 Ivan Donadello, Luciano Serafini, Artur d'Avila Garcez

Logic Tensor Networks (LTNs) are an 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.

Relational Reasoning Tensor Networks

On Coreferring Text-extracted Event Descriptions with the aid of Ontological Reasoning

no code implementations1 Dec 2016 Stefano Borgo, Loris Bozzato, Alessio Palmero Aprosio, Marco Rospocher, Luciano Serafini

Systems for automatic extraction of semantic information about events from large textual resources are now available: these tools are capable to generate RDF datasets about text extracted events and this knowledge can be used to reason over the recognized events.

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

2 code implementations14 Jun 2016 Luciano Serafini, Artur d'Avila Garcez

We propose Logic Tensor Networks: a uniform framework for integrating automatic learning and reasoning.

Tensor Networks

Query Answering over Contextualized RDF/OWL Knowledge with Forall-Existential Bridge Rules: Decidable Finite Extension Classes (Post Print)

no code implementations12 Dec 2015 Mathew Joseph, Gabriel Kuper, Till Mossakowski, Luciano Serafini

Sound, complete and terminating procedures, which are adaptations of the well known chase algorithm, are provided for these classes for deciding query entailment.

Semantic Enrichment of Mobile Phone Data Records Using Background Knowledge

no code implementations22 Apr 2015 Zolzaya Dashdorj, Stanislav Sobolevsky, Luciano Serafini, Fabrizio Antonelli, Carlo Ratti

This article addresses the issues in context awareness given heterogeneous and uncertain data of mobile network events missing reliable information on the context of this activity.

Knowledge Propagation in Contextualized Knowledge Repositories: an Experimental Evaluation

no code implementations26 Dec 2014 Loris Bozzato, Luciano Serafini

As the interest in the representation of context dependent knowledge in the Semantic Web has been recognized, a number of logic based solutions have been proposed in this regard.

Query Answering over Contextualized RDF/OWL Knowledge with Forall-Existential Bridge Rules: Attaining Decidability using Acyclicity (full version)

no code implementations3 Jun 2014 Mathew Joseph, Gabriel Kuper, Luciano Serafini

Quads, which extend a standard RDF triple, by adding a new parameter of the `context' of an RDF triple, thus informs a reasoner to distinguish between the knowledge in various contexts.

NewsReader: recording history from daily news streams

no code implementations LREC 2014 Piek Vossen, German Rigau, Luciano Serafini, Pim Stouten, Francis Irving, Willem van Hage

The European project NewsReader develops technology to process daily news streams in 4 languages, extracting what happened, when, where and who was involved.

The KnowledgeStore: an Entity-Based Storage System

no code implementations LREC 2012 Roldano Cattoni, Francesco Corcoglioniti, Christian Girardi, Bernardo Magnini, Luciano Serafini, Roberto Zanoli

The system allows (i) to import background knowledge about entities, in form of annotated RDF triples; (ii) to associate resources to entities by automatically recognizing, coreferring and linking mentions of named entities; and (iii) to derive new entities based on knowledge extracted from mentions.

Entity Extraction using GAN Entity Linking

Cannot find the paper you are looking for? You can Submit a new open access paper.