Search Results for author: Miguel Couceiro

Found 29 papers, 7 papers with code

GECko+: a Grammatical and Discourse Error Correction Tool

1 code implementation JEP/TALN/RECITAL 2021 Eduardo Calò, Léo Jacqmin, Thibo Rosemplatt, Maxime Amblard, Miguel Couceiro, Ajinkya Kulkarni

GECko+ : a Grammatical and Discourse Error Correction Tool We introduce GECko+, a web-based writing assistance tool for English that corrects errors both at the sentence and at the discourse level.

Sentence Sentence Ordering

Comparing representations of long clinical texts for the task of patient note-identification

no code implementations31 Mar 2025 Safa Alsaidi, Marc Vincent, Olivia Boyer, Nicolas Garcelon, Miguel Couceiro, Adrien Coulet

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.

Unveiling Biases while Embracing Sustainability: Assessing the Dual Challenges of Automatic Speech Recognition Systems

no code implementations2 Mar 2025 Ajinkya Kulkarni, Atharva Kulkarni, Miguel Couceiro, Isabel Trancoso

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.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1

Exploring ReAct Prompting for Task-Oriented Dialogue: Insights and Shortcomings

no code implementations2 Dec 2024 Michelle Elizabeth, Morgan Veyret, Miguel Couceiro, Ondrej Dusek, Lina M. Rojas-Barahona

Large language models (LLMs) gained immense popularity due to their impressive capabilities in unstructured conversations.

KGPrune: a Web Application to Extract Subgraphs of Interest from Wikidata with Analogical Pruning

no code implementations26 Aug 2024 Pierre Monnin, Cherif-Hassan Nousradine, Lucas Jarnac, Laurel Zuckerman, Miguel Couceiro

Knowledge graphs (KGs) have become ubiquitous publicly available knowledge sources, and are nowadays covering an ever increasing array of domains.

Knowledge Graphs

REFINE-LM: Mitigating Language Model Stereotypes via Reinforcement Learning

no code implementations18 Aug 2024 Rameez Qureshi, Naïm Es-Sebbani, Luis Galárraga, Yvette Graham, Miguel Couceiro, Zied Bouraoui

With the introduction of (large) language models, there has been significant concern about the unintended bias such models may inherit from their training data.

Language Modeling Language Modelling +2

Any four real numbers are on all fours with analogy

no code implementations26 Jul 2024 Yves Lepage, Miguel Couceiro

This work presents a formalization of analogy on numbers that relies on generalized means.

All

On the Calibration of Epistemic Uncertainty: Principles, Paradoxes and Conflictual Loss

1 code implementation16 Jul 2024 Mohammed Fellaji, Frédéric Pennerath, Brieuc Conan-Guez, Miguel Couceiro

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 Networks.

Classification

Uncertainty Management in the Construction of Knowledge Graphs: a Survey

no code implementations27 May 2024 Lucas Jarnac, Yoan Chabot, Miguel Couceiro

That is why recent efforts focus on automatic approaches, which represents a challenging task since it requires handling the uncertainty of extracted knowledge throughout its integration into the KG.

Knowledge Graphs Management +3

The Balancing Act: Unmasking and Alleviating ASR Biases in Portuguese

no code implementations12 Feb 2024 Ajinkya Kulkarni, Anna Tokareva, Rameez Qureshi, Miguel Couceiro

In the field of spoken language understanding, systems like Whisper and Multilingual Massive Speech (MMS) have shown state-of-the-art performances.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2

Adapting the adapters for code-switching in multilingual ASR

1 code implementation11 Oct 2023 Atharva Kulkarni, Ajinkya Kulkarni, Miguel Couceiro, Hanan Aldarmaki

Recently, large pre-trained multilingual speech models have shown potential in scaling Automatic Speech Recognition (ASR) to many low-resource languages.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1

Relevant Entity Selection: Knowledge Graph Bootstrapping via Zero-Shot Analogical Pruning

1 code implementation28 Jun 2023 Lucas Jarnac, Miguel Couceiro, Pierre Monnin

Knowledge Graph Construction (KGC) can be seen as an iterative process starting from a high quality nucleus that is refined by knowledge extraction approaches in a virtuous loop.

graph construction Transfer Learning

A statistical approach to detect sensitive features in a group fairness setting

no code implementations11 May 2023 Guilherme Dean Pelegrina, Miguel Couceiro, Leonardo Tomazeli Duarte

However, such an approach is subjective and does not guarantee that these features are the only ones to be considered as sensitive nor that they entail unfair (disparate) outcomes.

Fairness

Solving morphological analogies: from retrieval to generation

1 code implementation30 Mar 2023 Esteban Marquer, Miguel Couceiro

We propose a deep learning (DL) framework to address and tackle two key tasks in AR: analogy detection and solving.

Decision Making Retrieval

Survey on Fairness Notions and Related Tensions

no code implementations16 Sep 2022 Guilherme Alves, Fabien Bernier, Miguel Couceiro, Karima Makhlouf, Catuscia Palamidessi, Sami Zhioua

Fairness requirements to be satisfied while learning models created several types of tensions among the different notions of fairness and other desirable properties such as privacy and classification accuracy.

Fairness Survey

Component twin-width as a parameter for BINARY-CSP and its semiring generalisations

no code implementations14 Jul 2022 Ambroise Baril, Miguel Couceiro, Victor Lagerkvist

We illustrate the advantages of this framework by instantiating our general algorithmic approach on several classes of problems (e. g., the $H$-coloring problem and its variants), and showing that it improves the best complexity upper bounds in the literature for several well-known problems.

Galois theory for analogical classifiers

no code implementations9 May 2022 Miguel Couceiro, Erkko Lehtonen

Analogical proportions are 4-ary relations that read "A is to B as C is to D".

Tackling Morphological Analogies Using Deep Learning -- Extended Version

no code implementations9 Nov 2021 Safa Alsaidi, Amandine Decker, Esteban Marquer, Pierre-Alexandre Murena, Miguel Couceiro

We demonstrate our model's competitive performance on analogy detection and resolution over multiple languages.

Deep Learning

On the Transferability of Neural Models of Morphological Analogies

no code implementations9 Aug 2021 Safa Alsaidi, Amandine Decker, Puthineath Lay, Esteban Marquer, Pierre-Alexandre Murena, Miguel Couceiro

Analogical proportions are statements expressed in the form "A is to B as C is to D" and are used for several reasoning and classification tasks in artificial intelligence and natural language processing (NLP).

A Neural Approach for Detecting Morphological Analogies

no code implementations9 Aug 2021 Safa Alsaidi, Amandine Decker, Puthineath Lay, Esteban Marquer, Pierre-Alexandre Murena, Miguel Couceiro

In fact, symbolic approaches were developed to solve or to detect analogies between character strings, e. g., the axiomatic approach as well as that based on Kolmogorov complexity.

Reducing Unintended Bias of ML Models on Tabular and Textual Data

no code implementations5 Aug 2021 Guilherme Alves, Maxime Amblard, Fabien Bernier, Miguel Couceiro, Amedeo Napoli

Unintended biases in machine learning (ML) models are among the major concerns that must be addressed to maintain public trust in ML.

Fairness

A Bayesian Convolutional Neural Network for Robust Galaxy Ellipticity Regression

no code implementations20 Apr 2021 Claire Theobald, Bastien Arcelin, Frédéric Pennerath, Brieuc Conan-Guez, Miguel Couceiro, Amedeo Napoli

We show that while a convolutional network can be trained to correctly estimate well calibrated aleatoric uncertainty, -- the uncertainty due to the presence of noise in the images -- it is unable to generate a trustworthy ellipticity distribution when exposed to previously unseen data (i. e. here, blended scenes).

regression

A Bayesian Neural Network based on Dropout Regulation

no code implementations3 Feb 2021 Claire Theobald, Frédéric Pennerath, Brieuc Conan-Guez, Miguel Couceiro, Amedeo Napoli

Bayesian Neural Networks (BNN) have recently emerged in the Deep Learning world for dealing with uncertainty estimation in classification tasks, and are used in many application domains such as astrophysics, autonomous driving... BNN assume a prior over the weights of a neural network instead of point estimates, enabling in this way the estimation of both aleatoric and epistemic uncertainty of the model prediction. Moreover, a particular type of BNN, namely MC Dropout, assumes a Bernoulli distribution on the weights by using Dropout. Several attempts to optimize the dropout rate exist, e. g. using a variational approach. In this paper, we present a new method called "Dropout Regulation" (DR), which consists of automatically adjusting the dropout rate during training using a controller as used in automation. DR allows for a precise estimation of the uncertainty which is comparable to the state-of-the-art while remaining simple to implement.

Autonomous Driving

Making ML models fairer through explanations: the case of LimeOut

no code implementations1 Nov 2020 Guilherme Alves, Vaishnavi Bhargava, Miguel Couceiro, Amedeo Napoli

To illustrate, we will revisit the case of "LimeOut" that was proposed to tackle "process fairness", which measures a model's reliance on sensitive or discriminatory features.

Fairness

LimeOut: An Ensemble Approach To Improve Process Fairness

no code implementations17 Jun 2020 Vaishnavi Bhargava, Miguel Couceiro, Amedeo Napoli

To achieve both, we draw inspiration from "dropout" techniques in neural based approaches, and propose a framework that relies on "feature drop-out" to tackle process fairness.

Decision Making Fairness

Knowledge-Based Matching of $n$-ary Tuples

1 code implementation19 Feb 2020 Pierre Monnin, Miguel Couceiro, Amedeo Napoli, Adrien Coulet

In particular, units should be matched within and across sources, and their level of relatedness should be classified into equivalent, more specific, or similar.

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