no code implementations • 2 Feb 2024 • Daniel Cunnington, Mark Law, Jorge Lobo, Alessandra Russo
In this paper, we leverage the implicit knowledge within foundation models to enhance the performance in NeSy tasks, whilst reducing the amount of data labelling and manual engineering.
no code implementations • 18 Oct 2023 • Zlatina Mileva, Antonis Bikakis, Fabio Aurelio D'Asaro, Mark Law, Alessandra Russo
In this paper we present a novel framework, which uses an Inductive Logic Programming approach to learn the acceptability semantics for several abstract and structured argumentation frameworks in an interpretable way.
no code implementations • 8 Oct 2023 • Theo Charalambous, Yaniv Aspis, Alessandra Russo
Symbolic rule learners generate interpretable solutions, however they require the input to be encoded symbolically.
no code implementations • 28 Aug 2023 • Enrico Pontelli, Stefania Costantini, Carmine Dodaro, Sarah Gaggl, Roberta Calegari, Artur d'Avila Garcez, Francesco Fabiano, Alessandra Mileo, Alessandra Russo, Francesca Toni
This volume contains the Technical Communications presented at the 39th International Conference on Logic Programming (ICLP 2023), held at Imperial College London, UK from July 9 to July 15, 2023.
no code implementations • 9 Jul 2023 • Amrit Diggavi Seshadri, Alessandra Russo
Specifically, we propose a novel pipeline that extracts human-interpretable object-behaviour-facts from raw video clips and propose novel symbolic and transformer based reasoning methods that operate over these extracted facts to identify adverb-types.
no code implementations • 17 Jun 2023 • Rakhilya Lee Mekhtieva, Brandon Forbes, Dalal Alrajeh, Brendan Delaney, Alessandra Russo
By relying on support phrases mined from the SNOMED ontology, as well as predefined supported facts from values used in the RECAP (REmote COVID-19 Assessment in Primary Care) patient risk prediction tool, our graph generative framework is able to extract structured knowledge graphs from the highly unstructured and inconsistent format that consultation notes are written in.
1 code implementation • 11 Apr 2023 • Hadeel Al-Negheimish, Pranava Madhyastha, Alessandra Russo
Large pre-trained language models such as BERT have been widely used as a framework for natural language understanding (NLU) tasks.
2 code implementations • 29 Mar 2023 • Kexin Gu Baugh, Nuri Cingillioglu, Alessandra Russo
Neuro-symbolic rule learning has attracted lots of attention as it offers better interpretability than pure neural models and scales better than symbolic rule learning.
no code implementations • 24 Mar 2023 • Leo Ardon, Daniel Furelos-Blanco, Alessandra Russo
This paper presents a novel approach to Multi-Agent Reinforcement Learning (MARL) that combines cooperative task decomposition with the learning of reward machines (RMs) encoding the structure of the sub-tasks.
no code implementations • 15 Jul 2022 • Alex F. Spies, Alessandra Russo, Murray Shanahan
We investigate the composability of soft-rules learned by relational neural architectures when operating over object-centric (slot-based) representations, under a variety of sparsity-inducing constraints.
no code implementations • 21 Jun 2022 • Jeya Vikranth Jeyakumar, Luke Dickens, Luis Garcia, Yu-Hsi Cheng, Diego Ramirez Echavarria, Joseph Noor, Alessandra Russo, Lance Kaplan, Erik Blasch, Mani Srivastava
CoDEx identifies a rich set of complex concept abstractions from natural language explanations of videos-obviating the need to predefine the amorphous set of concepts.
1 code implementation • 31 May 2022 • Daniel Furelos-Blanco, Mark Law, Anders Jonsson, Krysia Broda, Alessandra Russo
Reward machines (RMs) are a recent formalism for representing the reward function of a reinforcement learning task through a finite-state machine whose edges encode subgoals of the task using high-level events.
1 code implementation • 25 May 2022 • Daniel Cunnington, Mark Law, Jorge Lobo, Alessandra Russo
A promising direction for achieving this goal is Neuro-Symbolic AI, which aims to combine the interpretability of symbolic techniques with the ability of deep learning to learn from raw data.
no code implementations • 29 Sep 2021 • Harald Stromfelt, Luke Dickens, Artur Garcez, Alessandra Russo
Human defined concepts are inherently transferable, but it is not clear under what conditions they can be modelled effectively by non-symbolic artificial learners.
no code implementations • EMNLP 2021 • Hadeel Al-Negheimish, Pranava Madhyastha, Alessandra Russo
The current standings of these models in the DROP leaderboard, over standard metrics, suggest that the models have achieved near-human performance.
1 code implementation • 24 Jun 2021 • Daniel Cunnington, Mark Law, Alessandra Russo, Jorge Lobo
To address this limitation, we propose a neural-symbolic learning framework, called Feed-Forward Neural-Symbolic Learner (FFNSL), that integrates a logic-based machine learning system capable of learning from noisy examples, with neural networks, in order to learn interpretable knowledge from labelled unstructured data.
3 code implementations • 14 Jun 2021 • Nuri Cingillioglu, Alessandra Russo
Humans have the ability to seamlessly combine low-level visual input with high-level symbolic reasoning often in the form of recognising objects, learning relations between them and applying rules.
no code implementations • EACL 2021 • Hadeel Al-Negheimish, Pranava Madhyastha, Alessandra Russo
Reasoning about information from multiple parts of a passage to derive an answer is an open challenge for reading-comprehension models.
no code implementations • 17 Jan 2021 • Theophile Sautory, Nuri Cingillioglu, Alessandra Russo
The task of Video Question Answering (VideoQA) consists in answering natural language questions about a video and serves as a proxy to evaluate the performance of a model in scene sequence understanding.
no code implementations • 1 Jan 2021 • Daniel Pace, Alessandra Russo, Murray Shanahan
Inspired by Quality-Diversity algorithms, in this work we train a collection of classifiers to learn distinct solutions to a classification problem, with the goal of learning to exploit a variety of predictive signals present in the training data.
no code implementations • 9 Dec 2020 • Daniel Cunnington, Alessandra Russo, Mark Law, Jorge Lobo, Lance Kaplan
Using the scoring function of FastLAS, NSL searches for short, interpretable rules that generalise over such noisy examples.
no code implementations • 13 Nov 2020 • Harald Strömfelt, Luke Dickens, Artur d'Avila Garcez, Alessandra Russo
We propose a new model for relational VAE semi-supervision capable of balancing disentanglement and low complexity modelling of relations with different symbolic properties.
no code implementations • 19 Oct 2020 • Amani Abu Jabal, Elisa Bertino, Jorge Lobo, Dinesh Verma, Seraphin Calo, Alessandra Russo
The design of a policy transfer framework has challenges, including policy conflicts and privacy issues.
Cryptography and Security
no code implementations • 19 Sep 2020 • Francesco Ricca, Alessandra Russo, Sergio Greco, Nicola Leone, Alexander Artikis, Gerhard Friedrich, Paul Fodor, Angelika Kimmig, Francesca Lisi, Marco Maratea, Alessandra Mileo, Fabrizio Riguzzi
Since the first conference held in Marseille in 1982, ICLP has been the premier international event for presenting research in logic programming.
no code implementations • 8 Sep 2020 • Daniel Furelos-Blanco, Mark Law, Anders Jonsson, Krysia Broda, Alessandra Russo
In this paper we present ISA, an approach for learning and exploiting subgoals in episodic reinforcement learning (RL) tasks.
no code implementations • 12 Jun 2020 • Daniel Pace, Alessandra Russo, Murray Shanahan
assumption is a useful idealization that underpins many successful approaches to supervised machine learning.
no code implementations • 2 May 2020 • Mark Law, Alessandra Russo, Krysia Broda
The goal of Inductive Logic Programming (ILP) is to learn a program that explains a set of examples in the context of some pre-existing background knowledge.
no code implementations • 2 Mar 2020 • David Tuckey, Alessandra Russo, Krysia Broda
Explainability in AI is gaining attention in the computer science community in response to the increasing success of deep learning and the important need of justifying how such systems make predictions in life-critical applications.
no code implementations • 29 Nov 2019 • Daniel Furelos-Blanco, Mark Law, Alessandra Russo, Krysia Broda, Anders Jonsson
In this work we present ISA, a novel approach for learning and exploiting subgoals in reinforcement learning (RL).
no code implementations • 27 Nov 2019 • Pawel Gomoluch, Dalal Alrajeh, Alessandra Russo, Antonio Bucchiarone
In this paper, we introduce a parametrized search algorithm template which combines various search techniques within a single routine.
1 code implementation • NeurIPS 2020 • Nuri Cingillioglu, Alessandra Russo
The core characteristic of our architecture is soft unification between examples that enables the network to generalise parts of the input into variables, thereby learning invariants.
no code implementations • 12 Jul 2019 • David Tuckey, Krysia Broda, Alessandra Russo
Saliency map generation techniques are at the forefront of explainable AI literature for a broad range of machine learning applications.
no code implementations • 23 Oct 2018 • Pawel Gomoluch, Dalal Alrajeh, Alessandra Russo
This enables using policy gradient to learn search strategies tailored to a specific distributions of planning problems and a selected performance metric, e. g. the IPC score.
no code implementations • 25 Aug 2018 • Mark Law, Alessandra Russo, Krysia Broda
In recent years, non-monotonic Inductive Logic Programming has received growing interest.
1 code implementation • 18 May 2018 • Nuri Cingillioglu, Alessandra Russo
Combining machine learning with logic-based expert systems in order to get the best of both worlds are becoming increasingly popular.
no code implementations • 21 Jul 2017 • Pawel Gomoluch, Dalal Alrajeh, Alessandra Russo, Antonio Bucchiarone
Automated planning remains one of the most general paradigms in Artificial Intelligence, providing means of solving problems coming from a wide variety of domains.
no code implementations • 5 Aug 2016 • Mark Law, Alessandra Russo, Krysia Broda
In ILP, examples must all be explained by a hypothesis together with a given background knowledge.
no code implementations • 23 Jul 2015 • Mark Law, Alessandra Russo, Krysia Broda
This paper contributes to the area of inductive logic programming by presenting a new learning framework that allows the learning of weak constraints in Answer Set Programming (ASP).