Search Results for author: Sylvain Lamprier

Found 22 papers, 11 papers with code

A RECURRENT NEURAL CASCADE-BASED MODEL FOR CONTINUOUS-TIME DIFFUSION PROCESS

no code implementations ICLR 2019 Sylvain Lamprier

Many works have been proposed in the literature to capture the dynamics of diffusion in networks.

Fairness without the sensitive attribute via Causal Variational Autoencoder

no code implementations10 Sep 2021 Vincent Grari, Sylvain Lamprier, Marcin Detyniecki

In recent years, most fairness strategies in machine learning models focus on mitigating unwanted biases by assuming that the sensitive information is observed.

Fairness

To Beam Or Not To Beam: That is a Question of Cooperation for Language GANs

no code implementations NeurIPS 2021 Thomas Scialom, Paul-Alexis Dray, Sylvain Lamprier, Benjamin Piwowarski, Jacopo Staiano

Due to the discrete nature of words, language GANs require to be optimized from rewards provided by discriminator networks, via reinforcement learning methods.

Question Generation

A Neural Tangent Kernel Perspective of GANs

2 code implementations10 Jun 2021 Jean-Yves Franceschi, Emmanuel de Bézenac, Ibrahim Ayed, Mickaël Chen, Sylvain Lamprier, Patrick Gallinari

We propose a novel theoretical framework of analysis for Generative Adversarial Networks (GANs).

Data-QuestEval: A Referenceless Metric for Data-to-Text Semantic Evaluation

2 code implementations EMNLP 2021 Clément Rebuffel, Thomas Scialom, Laure Soulier, Benjamin Piwowarski, Sylvain Lamprier, Jacopo Staiano, Geoffrey Scoutheeten, Patrick Gallinari

QuestEval is a reference-less metric used in text-to-text tasks, that compares the generated summaries directly to the source text, by automatically asking and answering questions.

Data-to-Text Generation Question Generation

Improving Robustness of Deep Reinforcement Learning Agents: Environment Attacks based on Critic Networks

no code implementations7 Apr 2021 Lucas Schott, Manon Césaire, Hatem Hajri, Sylvain Lamprier

Existing approaches of the literature to generate meaningful disturbances of the environment are adversarial reinforcement learning methods.

QuestEval: Summarization Asks for Fact-based Evaluation

2 code implementations EMNLP 2021 Thomas Scialom, Paul-Alexis Dray, Patrick Gallinari, Sylvain Lamprier, Benjamin Piwowarski, Jacopo Staiano, Alex Wang

Summarization evaluation remains an open research problem: current metrics such as ROUGE are known to be limited and to correlate poorly with human judgments.

Question Answering

Stochastic sparse adversarial attacks

2 code implementations24 Nov 2020 Manon Césaire, Hatem Hajri, Sylvain Lamprier, Patrick Gallinari

This paper introduces stochastic sparse adversarial attacks (SSAA), simple, fast and purely noise-based targeted and untargeted $L_0$ attacks of neural network classifiers (NNC).

Learning Unbiased Representations via Rényi Minimization

1 code implementation7 Sep 2020 Vincent Grari, Oualid El Hajouji, Sylvain Lamprier, Marcin Detyniecki

We leverage recent work which has been done to estimate this coefficient by learning deep neural network transformations and use it as a minmax game to penalize the intrinsic bias in a multi dimensional latent representation.

Fairness

Adversarial Learning for Counterfactual Fairness

no code implementations30 Aug 2020 Vincent Grari, Sylvain Lamprier, Marcin Detyniecki

In recent years, fairness has become an important topic in the machine learning research community.

Fairness

PDE-Driven Spatiotemporal Disentanglement

1 code implementation ICLR 2021 Jérémie Donà, Jean-Yves Franceschi, Sylvain Lamprier, Patrick Gallinari

A recent line of work in the machine learning community addresses the problem of predicting high-dimensional spatiotemporal phenomena by leveraging specific tools from the differential equations theory.

Discriminative Adversarial Search for Abstractive Summarization

1 code implementation ICML 2020 Thomas Scialom, Paul-Alexis Dray, Sylvain Lamprier, Benjamin Piwowarski, Jacopo Staiano

We introduce a novel approach for sequence decoding, Discriminative Adversarial Search (DAS), which has the desirable properties of alleviating the effects of exposure bias without requiring external metrics.

Abstractive Text Summarization Domain Adaptation

Fair Adversarial Gradient Tree Boosting

1 code implementation13 Nov 2019 Vincent Grari, Boris Ruf, Sylvain Lamprier, Marcin Detyniecki

The approach incorporates at each iteration the gradient of the neural network directly in the gradient tree boosting.

Fairness General Classification

Fairness-Aware Neural Réyni Minimization for Continuous Features

no code implementations12 Nov 2019 Vincent Grari, Boris Ruf, Sylvain Lamprier, Marcin Detyniecki

Second, by minimizing the HGR directly with an adversarial neural network architecture.

Fairness

Learning Dynamic Author Representations with Temporal Language Models

1 code implementation11 Sep 2019 Edouard Delasalles, Sylvain Lamprier, Ludovic Denoyer

By conditioning language models with author and temporal vector states, we are able to leverage the latent dependencies between the text contexts.

Information Retrieval Language Modelling

Answers Unite! Unsupervised Metrics for Reinforced Summarization Models

2 code implementations IJCNLP 2019 Thomas Scialom, Sylvain Lamprier, Benjamin Piwowarski, Jacopo Staiano

Abstractive summarization approaches based on Reinforcement Learning (RL) have recently been proposed to overcome classical likelihood maximization.

Abstractive Text Summarization Question Answering

A Variational Topological Neural Model for Cascade-based Diffusion in Networks

no code implementations28 Dec 2018 Sylvain Lamprier

Many works have been proposed in the literature to capture the dynamics of diffusion in networks.

Parameterized Neural Network Language Models for Information Retrieval

no code implementations6 Oct 2015 Benjamin Piwowarski, Sylvain Lamprier, Nicolas Despres

Although they present good abilities to cope with both term dependencies and vocabulary mismatch problems, thanks to the distributed representation of words they are based upon, such models could not be used readily in IR, where the estimation of one language model per document (or query) is required.

Information Retrieval Language Modelling

Learning Information Spread in Content Networks

no code implementations20 Dec 2013 Cédric Lagnier, Simon Bourigault, Sylvain Lamprier, Ludovic Denoyer, Patrick Gallinari

We introduce a model for predicting the diffusion of content information on social media.

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