I am a 3rd year PhD student at LIG, in the GETALP team and at Inria part of the Thoth team. I work on Image captioning and sequence to sequence prediction with deep neural networks under the supervision of Jakob Verbeek and Laurent Besacier. My PhD is part of the Decore project-team.
I graduated from Centrale Paris (Class of 2016) and Ecole normale supérieure de Cachan where I did my MVA master.
More details can be found in my resume.

Interests: Neural machine translation, image captioning, variational inference, probabilistic graphical models, metric learning and representation learning.
 maha.elbayad AT inria.fr  Google Scholar  GitHub  LinkedIn  Twitter
Publications
Pervasive Attention - 2D Convolutional Neural Networks for Sequence-to-Sequence Prediction
Maha Elbayad, Laurent Besacier, Jakob Verbeek
The SIGNLL Conference on Computational Natural Language Learning (CoNLL), 2018
ArXiv In proceedings Poster Code Bibtex
  @InProceedings{elbayad18conll,
    author ="Elbayad, Maha and Besacier, Laurent and Verbeek, Jakob",
    title = "Pervasive Attention: 2D Convolutional Neural Networks for Sequence-to-Sequence Prediction",
    booktitle = "Proceedings of the 22nd Conference on Computational Natural Language Learning",
    year = "2018",
 }
 
Token-level and sequence-level loss smoothing for RNN language models
Maha Elbayad, Laurent Besacier, Jakob Verbeek
Annual Meeting of the Association for Computational Linguistics (ACL), 2018
ArXiv In proceedings Slides Code Bibtex
  @InProceedings{elbayad18acl,
  author = "ELBAYAD, Maha and Besacier, Laurent and Verbeek, Jakob",
  title = "Token-level and sequence-level loss smoothing for RNN language models",
  booktitle = "Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
  year = "2018",
}
 
Talks