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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox
Picture for Marc Dymetman

Marc Dymetman

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



Tomasz Korbak , Hady Elsahar , Germán Kruszewski , Marc Dymetman

Figure 1 for On Reinforcement Learning and Distribution Matching for Fine-Tuning Language Models with no Catastrophic Forgetting
Figure 2 for On Reinforcement Learning and Distribution Matching for Fine-Tuning Language Models with no Catastrophic Forgetting
Figure 3 for On Reinforcement Learning and Distribution Matching for Fine-Tuning Language Models with no Catastrophic Forgetting
Figure 4 for On Reinforcement Learning and Distribution Matching for Fine-Tuning Language Models with no Catastrophic Forgetting

   Access Paper or Ask Questions

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



Bryan Eikema , Germán Kruszewski , Hady Elsahar , Marc Dymetman

Figure 1 for Sampling from Discrete Energy-Based Models with Quality/Efficiency Trade-offs
Figure 2 for Sampling from Discrete Energy-Based Models with Quality/Efficiency Trade-offs
Figure 3 for Sampling from Discrete Energy-Based Models with Quality/Efficiency Trade-offs
Figure 4 for Sampling from Discrete Energy-Based Models with Quality/Efficiency Trade-offs

   Access Paper or Ask Questions

Controlling Conditional Language Models with Distributional Policy Gradients



Tomasz Korbak , Hady Elsahar , German Kruszewski , Marc Dymetman

Figure 1 for Controlling Conditional Language Models with Distributional Policy Gradients
Figure 2 for Controlling Conditional Language Models with Distributional Policy Gradients
Figure 3 for Controlling Conditional Language Models with Distributional Policy Gradients
Figure 4 for Controlling Conditional Language Models with Distributional Policy Gradients
* 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

Figure 1 for Energy-Based Models for Code Generation under Compilability Constraints
Figure 2 for Energy-Based Models for Code Generation under Compilability Constraints
Figure 3 for Energy-Based Models for Code Generation under Compilability Constraints
Figure 4 for Energy-Based Models for Code Generation under Compilability Constraints
* 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

Figure 1 for A Distributional Approach to Controlled Text Generation
Figure 2 for A Distributional Approach to Controlled Text Generation
Figure 3 for A Distributional Approach to Controlled Text Generation
Figure 4 for A Distributional Approach to Controlled Text Generation
* 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

Figure 1 for Distributional Reinforcement Learning for Energy-Based Sequential Models
Figure 2 for Distributional Reinforcement Learning for Energy-Based Sequential Models
Figure 3 for Distributional Reinforcement Learning for Energy-Based Sequential Models
Figure 4 for Distributional Reinforcement Learning for Energy-Based Sequential Models
* 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

Figure 1 for Character-based NMT with Transformer
Figure 2 for Character-based NMT with Transformer
Figure 3 for Character-based NMT with Transformer
Figure 4 for Character-based NMT with Transformer

   Access Paper or Ask Questions

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



Alexandre BĂ©rard , Ioan Calapodescu , Marc Dymetman , Claude Roux , Jean-Luc Meunier , Vassilina Nikoulina

Figure 1 for Machine Translation of Restaurant Reviews: New Corpus for Domain Adaptation and Robustness
Figure 2 for Machine Translation of Restaurant Reviews: New Corpus for Domain Adaptation and Robustness
Figure 3 for Machine Translation of Restaurant Reviews: New Corpus for Domain Adaptation and Robustness
Figure 4 for Machine Translation of Restaurant Reviews: New Corpus for Domain Adaptation and Robustness
* WNGT 2019 Paper 
   Access Paper or Ask Questions

Global Autoregressive Models for Data-Efficient Sequence Learning



Tetiana Parshakova , Jean-Marc Andreoli , Marc Dymetman

Figure 1 for Global Autoregressive Models for Data-Efficient Sequence Learning
Figure 2 for Global Autoregressive Models for Data-Efficient Sequence Learning
Figure 3 for Global Autoregressive Models for Data-Efficient Sequence Learning
Figure 4 for Global Autoregressive Models for Data-Efficient Sequence Learning
* To appear in CONLL (The SIGNLL Conference on Computational Natural Language Learning) Hong Kong, Nov. 2019 
   Access Paper or Ask Questions
1
2
3
>>