1 code implementation • 19 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.
no code implementations • 17 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.
1 code implementation • 17 Jul 2020 • Pierre Monnin, Emmanuel Bresso, Miguel Couceiro, Malika Smaïl-Tabbone, Amedeo Napoli, Adrien Coulet
Features mined from knowledge graphs are widely used within multiple knowledge discovery tasks such as classification or fact-checking.
no code implementations • 1 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.
no code implementations • 3 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.
no code implementations • 20 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).
no code implementations • 5 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.
no code implementations • 9 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.
no code implementations • 9 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).
no code implementations • 9 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.
no code implementations • 9 May 2022 • Miguel Couceiro, Erkko Lehtonen
Analogical proportions are 4-ary relations that read "A is to B as C is to D".
no code implementations • 14 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.
no code implementations • 16 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.
no code implementations • 22 Nov 2022 • Claire Theobald, Frédéric Pennerath, Brieuc Conan-Guez, Miguel Couceiro, Amedeo Napoli
Visual counterfactual explanations identify modifications to an image that would change the prediction of a classifier.
1 code implementation • 30 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.
no code implementations • 11 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.
1 code implementation • 28 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.
1 code implementation • 11 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
no code implementations • 12 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
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.