Paul Michel

Publication Activity (10 Years)

Years Active: 2016-2024
Publications (10 Years): 43

Top Topics

Machine Translation

Brazilian Portuguese

Multitask Learning

Top Venues

Publications

Mathieu Rita, Florian Strub, Rahma Chaabouni, Paul Michel, Emmanuel Dupoux, Olivier Pietquin
Countering Reward Over-Optimization in LLM with Demonstration-Guided Reinforcement Learning. ACL (Findings) (2024)
Mathieu Rita, Paul Michel, Rahma Chaabouni, Olivier Pietquin, Emmanuel Dupoux, Florian Strub
Language Evolution with Deep Learning. CoRR (2024)
Heri Zhao, Jeffrey Hui, Joshua Howland, Nam Nguyen, Siqi Zuo, Andrea Hu, Christopher A. Choquette-Choo, Jingyue Shen, Joe Kelley, Kshitij Bansal, Luke Vilnis, Mateo Wirth, Paul Michel, Peter Choy, Pratik Joshi, Ravin Kumar, Sarmad Hashmi, Shubham Agrawal, Zhitao Gong, Jane Fine, Tris Warkentin, Ale Jakse Hartman, Bin Ni, Kathy Korevec, Kelly Schaefer, Scott Huffman
CodeGemma: Open Code Models Based on Gemma. CoRR (2024)
Mathieu Rita, Florian Strub, Rahma Chaabouni, Paul Michel, Emmanuel Dupoux, Olivier Pietquin
Countering Reward Over-optimization in LLM with Demonstration-Guided Reinforcement Learning. CoRR (2024)
Lucas Weber, Jaap Jumelet, Paul Michel, Elia Bruni, Dieuwke Hupkes
Curriculum Learning with Adam: The Devil Is in the Wrong Details. CoRR (2023)
Valentin Taillandier, Dieuwke Hupkes, Benoît Sagot, Emmanuel Dupoux, Paul Michel
Neural Agents Struggle to Take Turns in Bidirectional Emergent Communication. ICLR (2023)
Lucio M. Dery, Paul Michel, Mikhail Khodak, Graham Neubig, Ameet Talwalkar
AANG : Automating Auxiliary Learning. ICLR (2023)
Paul Michel, Mathieu Rita, Kory Wallace Mathewson, Olivier Tieleman, Angeliki Lazaridou
Revisiting Populations in multi-agent Communication. ICLR (2023)
Mathieu Rita, Corentin Tallec, Paul Michel, Jean-Bastien Grill, Olivier Pietquin, Emmanuel Dupoux, Florian Strub
Emergent Communication: Generalization and Overfitting in Lewis Games. NeurIPS (2022)
Paul Michel, Tatsunori Hashimoto, Graham Neubig
Distributionally Robust Models with Parametric Likelihood Ratios. CoRR (2022)
Lucio M. Dery, Paul Michel, Mikhail Khodak, Graham Neubig, Ameet Talwalkar
AANG: Automating Auxiliary Learning. CoRR (2022)
Lucio M. Dery, Paul Michel, Ameet Talwalkar, Graham Neubig
Should We Be Pre-training? An Argument for End-task Aware Training as an Alternative. ICLR (2022)
Paul Michel, Tatsunori Hashimoto, Graham Neubig
Distributionally Robust Models with Parametric Likelihood Ratios. ICLR (2022)
Mathieu Rita, Corentin Tallec, Paul Michel, Jean-Bastien Grill, Olivier Pietquin, Emmanuel Dupoux, Florian Strub
Emergent Communication: Generalization and Overfitting in Lewis Games. CoRR (2022)
Paul Michel, Tatsunori Hashimoto, Graham Neubig
Modeling the Second Player in Distributionally Robust Optimization. ICLR (2021)
Paul Michel, Sebastian Ruder, Dani Yogatama
Balancing Average and Worst-case Accuracy in Multitask Learning. CoRR (2021)
Chunting Zhou, Xuezhe Ma, Paul Michel, Graham Neubig
Examining and Combating Spurious Features under Distribution Shift. ICML (2021)
Paul Michel, Tatsunori Hashimoto, Graham Neubig
Modeling the Second Player in Distributionally Robust Optimization. CoRR (2021)
Paul Michel
Learning Neural Models for Natural Language Processing in the Face of Distributional Shift. CoRR (2021)
Chunting Zhou, Xuezhe Ma, Paul Michel, Graham Neubig
Examining and Combating Spurious Features under Distribution Shift. CoRR (2021)
Lucio M. Dery, Paul Michel, Ameet Talwalkar, Graham Neubig
Should We Be Pre-training? An Argument for End-task Aware Training as an Alternative. CoRR (2021)
Xinyi Wang, Hieu Pham, Paul Michel, Antonios Anastasopoulos, Jaime G. Carbonell, Graham Neubig
Optimizing Data Usage via Differentiable Rewards. ICML (2020)
Keita Kurita, Paul Michel, Graham Neubig
Weight Poisoning Attacks on Pretrained Models. ACL (2020)
Lucia Specia, Zhenhao Li, Juan Miguel Pino, Vishrav Chaudhary, Francisco Guzmán, Graham Neubig, Nadir Durrani, Yonatan Belinkov, Philipp Koehn, Hassan Sajjad, Paul Michel, Xian Li
Findings of the WMT 2020 Shared Task on Machine Translation Robustness. WMT@EMNLP (2020)
Keita Kurita, Paul Michel, Graham Neubig
Weight Poisoning Attacks on Pre-trained Models. CoRR (2020)
Xian Li, Paul Michel, Antonios Anastasopoulos, Yonatan Belinkov, Nadir Durrani, Orhan Firat, Philipp Koehn, Graham Neubig, Juan Miguel Pino, Hassan Sajjad
Findings of the First Shared Task on Machine Translation Robustness. CoRR (2019)
Paul Michel, Xian Li, Graham Neubig, Juan Miguel Pino
On Evaluation of Adversarial Perturbations for Sequence-to-Sequence Models. NAACL-HLT (1) (2019)
Graham Neubig, Zi-Yi Dou, Junjie Hu, Paul Michel, Danish Pruthi, Xinyi Wang
compare-mt: A Tool for Holistic Comparison of Language Generation Systems. CoRR (2019)
Paul Michel, Omer Levy, Graham Neubig
Are Sixteen Heads Really Better than One? NeurIPS (2019)
Xian Li, Paul Michel, Antonios Anastasopoulos, Yonatan Belinkov, Nadir Durrani, Orhan Firat, Philipp Koehn, Graham Neubig, Juan Miguel Pino, Hassan Sajjad
Findings of the First Shared Task on Machine Translation Robustness. WMT (2) (2019)
Paul Michel, Xian Li, Graham Neubig, Juan Miguel Pino
On Evaluation of Adversarial Perturbations for Sequence-to-Sequence Models. CoRR (2019)
Paul Michel, Omer Levy, Graham Neubig
Are Sixteen Heads Really Better than One? CoRR (2019)
Graham Neubig, Zi-Yi Dou, Junjie Hu, Paul Michel, Danish Pruthi, Xinyi Wang
compare-mt: A Tool for Holistic Comparison of Language Generation Systems. NAACL-HLT (Demonstrations) (2019)
Xinyi Wang, Hieu Pham, Paul Michel, Antonios Anastasopoulos, Graham Neubig, Jaime G. Carbonell
Optimizing Data Usage via Differentiable Rewards. CoRR (2019)
Paul Michel, Graham Neubig
MTNT: A Testbed for Machine Translation of Noisy Text. CoRR (2018)
Paul Michel, Graham Neubig
Extreme Adaptation for Personalized Neural Machine Translation. CoRR (2018)
Paul Michel, Graham Neubig
MTNT: A Testbed for Machine Translation of Noisy Text. EMNLP (2018)
Paul Michel, Graham Neubig
Extreme Adaptation for Personalized Neural Machine Translation. ACL (2) (2018)
Paul Michel, Abhilasha Ravichander, Shruti Rijhwani
Does the Geometry of Word Embeddings Help Document Classification? A Case Study on Persistent Homology Based Representations. CoRR (2017)
Paul Michel, Abhilasha Ravichander, Shruti Rijhwani
Does the Geometry of Word Embeddings Help Document Classification? A Case Study on Persistent Homology-Based Representations. Rep4NLP@ACL (2017)
Graham Neubig, Chris Dyer, Yoav Goldberg, Austin Matthews, Waleed Ammar, Antonios Anastasopoulos, Miguel Ballesteros, David Chiang, Daniel Clothiaux, Trevor Cohn, Kevin Duh, Manaal Faruqui, Cynthia Gan, Dan Garrette, Yangfeng Ji, Lingpeng Kong, Adhiguna Kuncoro, Gaurav Kumar, Chaitanya Malaviya, Paul Michel, Yusuke Oda, Matthew Richardson, Naomi Saphra, Swabha Swayamdipta, Pengcheng Yin
DyNet: The Dynamic Neural Network Toolkit. CoRR (2017)
Paul Michel, Okko Räsänen, Roland Thiollière, Emmanuel Dupoux
Blind Phoneme Segmentation With Temporal Prediction Errors. ACL (Student Research Workshop) (2017)
Paul Michel, Okko Räsänen, Roland Thiollière, Emmanuel Dupoux
Improving Phoneme segmentation with Recurrent Neural Networks. CoRR (2016)