Search Results for author: Julien Perez

Found 21 papers, 1 papers with code

SLIM: Skill Learning with Multiple Critics

no code implementations1 Feb 2024 David Emukpere, Bingbing Wu, Julien Perez

Self-supervised skill learning aims to acquire useful behaviors that leverage the underlying dynamics of the environment.

Hierarchical Reinforcement Learning

LARG, Language-based Automatic Reward and Goal Generation

no code implementations19 Jun 2023 Julien Perez, Denys Proux, Claude Roux, Michael Niemaz

To leverage reinforcement learning with text-based task descriptions, we need to produce reward functions associated with individual tasks in a scalable manner.

reinforcement-learning

Globalizing BERT-based Transformer Architectures for Long Document Summarization

no code implementations EACL 2021 Quentin Grail, Julien Perez, Eric Gaussier

Fine-tuning a large language model on downstream tasks has become a commonly adopted process in the Natural Language Processing (NLP) (CITATION).

Document Summarization Extractive Summarization +2

Learning Visual Representations with Caption Annotations

no code implementations ECCV 2020 Mert Bulent Sariyildiz, Julien Perez, Diane Larlus

Starting from the observation that captioned images are easily crawlable, we argue that this overlooked source of information can be exploited to supervise the training of visual representations.

Image Captioning Language Modelling +1

Improving the Generalization of Visual Navigation Policies using Invariance Regularization

no code implementations ICLR 2020 Michel Aractingi, Christopher Dance, Julien Perez, Tomi Silander

The results of this method, called invariance regularization, show an improvement in the generalization of policies to environments not seen during training.

Reinforcement Learning (RL) Visual Navigation

ReviewQA: a relational aspect-based opinion reading dataset

no code implementations29 Oct 2018 Quentin Grail, Julien Perez

To motivate this purpose, we present ReviewQA, a question-answering dataset based on hotel reviews.

Question Answering

DEEP ADVERSARIAL FORWARD MODEL

no code implementations27 Sep 2018 Morgan Funtowicz, Tomi Silander, Arnaud Sors, Julien Perez

More precisely, our forward model is trained to produce realistic observations of the future while a discriminator model is trained to distinguish between real images and the model’s prediction of the future.

Image Generation Reinforcement Learning (RL)

Adversarial reading networks for machine comprehension

no code implementations ICLR 2018 Quentin Grail, Julien Perez

In this paper we explore the paradigm of adversarial learning and self-play for the task of machine reading comprehension.

Machine Reading Comprehension Question Answering

Contextual memory bandit for pro-active dialog engagement

no code implementations ICLR 2018 julien perez, Tomi Silander

In this paper, we propose to introduce the paradigm of contextual bandits as framework for pro-active dialog systems.

Multi-Armed Bandits

Non-Markovian Control with Gated End-to-End Memory Policy Networks

no code implementations31 May 2017 Julien Perez, Tomi Silander

In this paper, we explore the use of a recently proposed attention-based model, the Gated End-to-End Memory Network, for sequential control.

OpenAI Gym

A Recurrent and Compositional Model for Personality Trait Recognition from Short Texts

no code implementations WS 2016 Fei Liu, Julien Perez, Scott Nowson

Many methods have been used to recognise author personality traits from text, typically combining linguistic feature engineering with shallow learning models, e. g. linear regression or Support Vector Machines.

Feature Engineering Part-Of-Speech Tagging +4

A Language-independent and Compositional Model for Personality Trait Recognition from Short Texts

no code implementations EACL 2017 Fei Liu, Julien Perez, Scott Nowson

Many methods have been used to recognize author personality traits from text, typically combining linguistic feature engineering with shallow learning models, e. g. linear regression or Support Vector Machines.

Feature Engineering Personality Trait Recognition +2

Gated End-to-End Memory Networks

1 code implementation EACL 2017 Julien Perez, Fei Liu

Our experiments show significant improvements on the most challenging tasks in the 20 bAbI dataset, without the use of any domain knowledge.

dialog state tracking Question Answering +1

Spectral decomposition method of dialog state tracking via collective matrix factorization

no code implementations16 Jun 2016 Julien Perez

Finally, we show that the prediction schema is computationally efficient in comparison to the previous approaches.

dialog state tracking Management +3

Dialog state tracking, a machine reading approach using Memory Network

no code implementations EACL 2017 Julien Perez, Fei Liu

In an end-to-end dialog system, the aim of dialog state tracking is to accurately estimate a compact representation of the current dialog status from a sequence of noisy observations produced by the speech recognition and the natural language understanding modules.

dialog state tracking Management +5

Online Learning to Sample

no code implementations30 Jun 2015 Guillaume Bouchard, Théo Trouillon, Julien Perez, Adrien Gaidon

Stochastic Gradient Descent (SGD) is one of the most widely used techniques for online optimization in machine learning.

Image Classification

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