Miguel Couceiro
YOU?
Author Swipe
View article: WikiConflict: A New Dataset for Conflicting Data Reconciliation in Knowledge Graph Construction
WikiConflict: A New Dataset for Conflicting Data Reconciliation in Knowledge Graph Construction Open
View article: TrustFuse: A Fusion Testbed for Uncertain Knowledge Reconciliation
TrustFuse: A Fusion Testbed for Uncertain Knowledge Reconciliation Open
View article: New Perspectives on Semiring Applications to Dynamic Programming
New Perspectives on Semiring Applications to Dynamic Programming Open
Semiring algebras have been shown to provide a suitable language to formalize many noteworthy combinatorial problems. For instance, the Shortest-Path problem can be seen as a special case of the Algebraic-Path problem when applied to the t…
View article: Generalizing Analogical Inference from Boolean to Continuous Domains
Generalizing Analogical Inference from Boolean to Continuous Domains Open
Analogical reasoning is a powerful inductive mechanism, widely used in human cognition and increasingly applied in artificial intelligence. Formal frameworks for analogical inference have been developed for Boolean domains, where inference…
View article: Improved Bounds for Twin-Width Parameter Variants with Algorithmic Applications to Counting Graph Colorings
Improved Bounds for Twin-Width Parameter Variants with Algorithmic Applications to Counting Graph Colorings Open
The $H$-Coloring problem is a well-known generalization of the classical NP-complete problem $k$-Coloring where the task is to determine whether an input graph admits a homomorphism to the template graph $H$. This problem has been the subj…
View article: Proceedings of the 4th Workshop on the Interactions between Analogical Reasoning and Machine Learning (IARML 2025) co-located with the International Joint Conference on Artificial Intelligence (IJCAI 2025)
Proceedings of the 4th Workshop on the Interactions between Analogical Reasoning and Machine Learning (IARML 2025) co-located with the International Joint Conference on Artificial Intelligence (IJCAI 2025) Open
International audience
View article: Game-theoretic extensions of logistic regression
Game-theoretic extensions of logistic regression Open
View article: Comparing representations of long clinical texts for the task of patient note-identification
Comparing representations of long clinical texts for the task of patient note-identification Open
In this paper, we address the challenge of patient-note identification, which involves accurately matching an anonymized clinical note to its corresponding patient, represented by a set of related notes. This task has broad applications, i…
View article: EDAR: A pipeline for Emotion and Dialogue Act Recognition
EDAR: A pipeline for Emotion and Dialogue Act Recognition Open
International audience
View article: Comparing representations of long clinical texts for the task of patient-note identification
Comparing representations of long clinical texts for the task of patient-note identification Open
View article: Preface to the special issue on analogies: from mathematical foundations to applications and interactions with ML and AI
Preface to the special issue on analogies: from mathematical foundations to applications and interactions with ML and AI Open
View article: Exploring ReAct Prompting for Task-Oriented Dialogue: Insights and Shortcomings
Exploring ReAct Prompting for Task-Oriented Dialogue: Insights and Shortcomings Open
Large language models (LLMs) gained immense popularity due to their impressive capabilities in unstructured conversations. Empowering LLMs with advanced prompting strategies such as reasoning and acting (ReAct) (Yao et al., 2022) has shown…
View article: REFINE-LM: Mitigating Language Model Stereotypes via Reinforcement Learning
REFINE-LM: Mitigating Language Model Stereotypes via Reinforcement Learning Open
With the introduction of (large) language models, there has been significant concern about the unintended bias such models may inherit from their training data. A number of studies have shown that such models propagate gender stereotypes, …
View article: KGPRUNE: A Web Application to Extract Subgraphs of Interest from Wikidata with Analogical Pruning
KGPRUNE: A Web Application to Extract Subgraphs of Interest from Wikidata with Analogical Pruning Open
Knowledge graphs (KGs) have become ubiquitous publicly available knowledge sources, and are nowadays covering an ever increasing array of domains. However, not all knowledge represented is useful or pertaining when considering a new applic…
View article: ORPAILLEUR & SyNaLP at CLEF 2024 Task 2: Good Old Cross Validation for Large Language Models Yields the Best Humorous Detection
ORPAILLEUR & SyNaLP at CLEF 2024 Task 2: Good Old Cross Validation for Large Language Models Yields the Best Humorous Detection Open
International audience
View article: Unveiling Biases while Embracing Sustainability: Assessing the Dual Challenges of Automatic Speech Recognition Systems
Unveiling Biases while Embracing Sustainability: Assessing the Dual Challenges of Automatic Speech Recognition Systems Open
In this paper, we present a bias and sustainability focused investigation of Automatic Speech Recognition (ASR) systems, namely Whisper and Massively Multilingual Speech (MMS), which have achieved state-of-the-art (SOTA) performances. Desp…
View article: KGPrune: a Web Application to Extract Subgraphs of Interest from Wikidata with Analogical Pruning
KGPrune: a Web Application to Extract Subgraphs of Interest from Wikidata with Analogical Pruning Open
Knowledge graphs (KGs) have become ubiquitous publicly available knowledge sources, and are nowadays covering an ever increasing array of domains. However, not all knowledge represented is useful or pertaining when considering a new applic…
View article: REFINE-LM: Mitigating Language Model Stereotypes via Reinforcement Learning
REFINE-LM: Mitigating Language Model Stereotypes via Reinforcement Learning Open
With the introduction of (large) language models, there has been significant concern about the unintended bias such models may inherit from their training data. A number of studies have shown that such models propagate gender stereotypes, …
View article: Any four real numbers are on all fours with analogy
Any four real numbers are on all fours with analogy Open
This work presents a formalization of analogy on numbers that relies on generalized means. It is motivated by recent advances in artificial intelligence and applications of machine learning, where the notion of analogy is used to infer res…
View article: On the Calibration of Epistemic Uncertainty: Principles, Paradoxes and Conflictual Loss
On the Calibration of Epistemic Uncertainty: Principles, Paradoxes and Conflictual Loss Open
The calibration of predictive distributions has been widely studied in deep learning, but the same cannot be said about the more specific epistemic uncertainty as produced by Deep Ensembles, Bayesian Deep Networks, or Evidential Deep Netwo…
View article: Analogie et moyenne généralisée
Analogie et moyenne généralisée Open
National audience
View article: Solving morphological analogies: from retrieval to generation
Solving morphological analogies: from retrieval to generation Open
View article: A preprocessing Shapley value-based approach to detect relevant and disparity prone features in machine learning
A preprocessing Shapley value-based approach to detect relevant and disparity prone features in machine learning Open
International audience
View article: Uncertainty Management in the Construction of Knowledge Graphs: a Survey
Uncertainty Management in the Construction of Knowledge Graphs: a Survey Open
Knowledge Graphs (KGs) are a major asset for companies thanks to their great flexibility in data representation and their numerous applications, e.g., vocabulary sharing, Q/A or recommendation systems. To build a KG it is a common practice…
View article: A survey on the enumeration of classes of logical connectives and aggregation functions defined on a finite chain, with new results
A survey on the enumeration of classes of logical connectives and aggregation functions defined on a finite chain, with new results Open
International audience
View article: The Fine-Grained Complexity of Graph Homomorphism Problems: Towards the Okrasa and Rzążewski Conjecture
The Fine-Grained Complexity of Graph Homomorphism Problems: Towards the Okrasa and Rzążewski Conjecture Open
In this paper we are interested in the fine-grained complexity of deciding whether there is a homomorphism from an input graph $G$ to a fixed graph $H$ (the $H$-Coloring problem). The starting point is that these problems can be viewed as …
View article: The Fine-Grained Complexity of Graph Homomorphism Problems: Towards the\n Okrasa and Rz\\k{a}\\.zewski Conjecture
The Fine-Grained Complexity of Graph Homomorphism Problems: Towards the\n Okrasa and Rz\\k{a}\\.zewski Conjecture Open
In this paper we are interested in the fine-grained complexity of deciding\nwhether there is a homomorphism from an input graph $G$ to a fixed graph $H$\n(the $H$-Coloring problem). The starting point is that these problems can be\nviewed …
View article: The Balancing Act: Unmasking and Alleviating ASR Biases in Portuguese
The Balancing Act: Unmasking and Alleviating ASR Biases in Portuguese Open
In the field of spoken language understanding, systems like Whisper and Multilingual Massive Speech (MMS) have shown state-of-the-art performances. This study is dedicated to a comprehensive exploration of the Whisper and MMS systems, with…
View article: Clarity: a Deep Ensemble for Visual Counterfactual Explanations
Clarity: a Deep Ensemble for Visual Counterfactual Explanations Open
International audience
View article: 2023 Activity Report -- Orpailleur Team (LORIA) : Knowledge Discovery and Knowledge Engineering
2023 Activity Report -- Orpailleur Team (LORIA) : Knowledge Discovery and Knowledge Engineering Open
The research topics of the Orpailleur Team of 2023 gravitated the federating theme “Exploratory and hybrid knowledge discovery” of the team, but opened to new research directions, such as, “Explainability, transparence and fairness” and “A…