Hady Elsahar | Naver Labs Europe
Change your cover photo
Change your cover photo
This user account status is Approved

This user has not added any information to their profile yet.

Natural Language Processing

For more details check Hady's updated personal website: hadyelsahar.io

Hady is a Research Scientist and project lead in the Natural Language Processing team in NAVER Labs Europe. He is particularly interested in Neural Language Generation under constrained and controlled conditions, for applications such as Controlling large language modelsUnsupervisedZero-Shot, and Few shot NLG. He is mostly interested in Sequential Energy Based Models, MCMC samplers, Reinforcement Learning and its distributional adaptations.

Hady holds a PhD. Degree from L'Université de Lyon advised by Christophe Gravier and Frederique Laforest . His thesis was on Learning representations for Natural Language Generation and Structured Knowledge bases for Data2Text Generation and Relation Extraction & Discovery.  Prior to that, He got his Masters Degree from Nile University in Cairo where he worked on Low-resource sentiment analysis. 

  • Apr 2, 2021: Talk at Deep Learning: Classics and Trends on “A Distributional Approach to Controlled Text Generation” [Paper] [slides soon]

  • Mar 3, 2021: Talk at RECITAL, Paris on “Controlling Stochastic Parrots” [slides]

  • Feb 26, 2021: Giving a course lecture on Neural Language Generation “NLG Head to Toe”- DSBA master of CentraleSupélec, Paris, France [slides]

  • Jan 28 2021: Holding a mentorship session on “How to write Rebuttals for Scientific conference" [Slides]

  • Jan 15, 2021: Accepted paper at ICLR2021 (Oral): A Distributional Approach to Controlled Text Generation [Paper] [Twitter Summary]

  • Jan 13, 2021:  Accepted Paper at EACL2021: Self-Supervised and Controlled Multi-Document Opinion Summarization [Paper] [Twitter Summary]

  • Dec 18, 2021:  Co-organizing Energy-Based Models Workshop @ ICLR 2021 [Workshop Website] [Twitter 🐦]

  • Dec 15, 2021:  Co-organizing AfricaNLP Workshop @ EACL 2021 [Workshop Website] (Mentorship Program)

  • Nov 7, 2020:  Accepted paper at EMNLP2020/Fndings: Participatory Research for Low-resourced Machine Translation [Paper] [Code] [summary]

  • Apr 3 2020:  Two talks at Bloomberg London and UCL on “Predicting When Machine Learning Models Fail” [Slides]

- Feb 26, 2021: Neural Language Generation DSBA master of CentraleSupélec, Paris, France  [Slides]