Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

On Reinforcement Learning and Distribution Matching for Fine-Tuning Language Models with no Catastrophic Forgetting



Tomasz Korbak , Hady Elsahar , Germán Kruszewski , Marc Dymetman


   Access Paper or Ask Questions

Sampling from Discrete Energy-Based Models with Quality/Efficiency Trade-offs



Bryan Eikema , Germán Kruszewski , Hady Elsahar , Marc Dymetman


   Access Paper or Ask Questions

Controlling Conditional Language Models with Distributional Policy Gradients



Tomasz Korbak , Hady Elsahar , German Kruszewski , Marc Dymetman

* CtrlGen: Controllable Generative Modeling in Language and Vision Workshop at NeurIPS 2021 

   Access Paper or Ask Questions

Energy-Based Models for Code Generation under Compilability Constraints



Tomasz Korbak , Hady Elsahar , Marc Dymetman , Germán Kruszewski

* Accepted for the First Workshop on Natural Language Processing for Programming, ACL 2021 

   Access Paper or Ask Questions

A Distributional Approach to Controlled Text Generation



Muhammad Khalifa , Hady Elsahar , Marc Dymetman

* Under review at ICLR 2021 

   Access Paper or Ask Questions

Distributional Reinforcement Learning for Energy-Based Sequential Models



Tetiana Parshakova , Jean-Marc Andreoli , Marc Dymetman

* OptRL workshop (Optimization Foundations for Reinforcement Learning) at Neurips 2019 

   Access Paper or Ask Questions

Character-based NMT with Transformer



Rohit Gupta , Laurent Besacier , Marc Dymetman , Matthias Gallé


   Access Paper or Ask Questions

Machine Translation of Restaurant Reviews: New Corpus for Domain Adaptation and Robustness



Alexandre Bérard , Ioan Calapodescu , Marc Dymetman , Claude Roux , Jean-Luc Meunier , Vassilina Nikoulina

* WNGT 2019 Paper 

   Access Paper or Ask Questions

Global Autoregressive Models for Data-Efficient Sequence Learning



Tetiana Parshakova , Jean-Marc Andreoli , Marc Dymetman

* To appear in CONLL (The SIGNLL Conference on Computational Natural Language Learning) Hong Kong, Nov. 2019 

   Access Paper or Ask Questions

1
2
3
>>