Attribute Controlled Dialogue Prompting F i n d i n g s - A C L

Runcheng Liu | Ahmad Rashid | Ivan Kobyzev | Mehdi Rezagholizadeh | Pascal Poupart |

LABO: Towards Learning Optimal Label Regularization via Bi-level Optimization F i n d i n g s - A C L

Peng Lu | Ahmad Rashid | Ivan Kobyzev | Mehdi Rezagholizadeh | Phillippe Langlais |

Kronecker Decomposition for GPT Compression ACL

Ali Edalati | Marzieh Tahaei | Ahmad Rashid | Vahid Nia | James Clark | Mehdi Rezagholizadeh |

Revisiting Pre-trained Language Models and their Evaluation for Arabic Natural Language Processing EMNLP

Abbas Ghaddar | Yimeng Wu | Sunyam Bagga | Ahmad Rashid | Khalil Bibi | Mehdi Rezagholizadeh | Chao Xing | Yasheng Wang | Xinyu Duan | Zhefeng Wang | Baoxing Huai | Xin Jiang | Qun Liu | Phillippe Langlais |

Improving Generalization of Pre-trained Language Models via Stochastic Weight Averaging F i n d i n g s - E M N L P

Peng Lu | Ivan Kobyzev | Mehdi Rezagholizadeh | Ahmad Rashid | Ali Ghodsi | Phillippe Langlais |

Context-aware Adversarial Training for Name Regularity Bias in Named Entity Recognition TACL

Abbas Ghaddar | Philippe Langlais | Ahmad Rashid | Mehdi Rezagholizadeh |

End-to-End Self-Debiasing Framework for Robust NLU Training Findings

Abbas Ghaddar | Phillippe Langlais | Mehdi Rezagholizadeh | Ahmad Rashid |

Towards Zero-Shot Knowledge Distillation for Natural Language Processing EMNLP

Ahmad Rashid | Vasileios Lioutas | Abbas Ghaddar | Mehdi Rezagholizadeh |

RW-KD: Sample-wise Loss Terms Re-Weighting for Knowledge Distillation EMNLP Findings

Peng Lu | Abbas Ghaddar | Ahmad Rashid | Mehdi Rezagholizadeh | Ali Ghodsi | Philippe Langlais |

MATE-KD: Masked Adversarial TExt, a Companion to Knowledge Distillation ACL IJCNLP

Ahmad Rashid | Vasileios Lioutas | Mehdi Rezagholizadeh |

How to Select One Among All ? An Empirical Study Towards the Robustness of Knowledge Distillation in Natural Language Understanding EMNLP Findings

Tianda Li | Ahmad Rashid | Aref Jafari | Pranav Sharma | Ali Ghodsi | Mehdi Rezagholizadeh |

Knowledge Distillation with Noisy Labels for Natural Language Understanding EMNLP WNUT

Shivendra Bhardwaj | Abbas Ghaddar | Ahmad Rashid | Khalil Bibi | Chengyang Li | Ali Ghodsi | Phillippe Langlais | Mehdi Rezagholizadeh |

Improving Word Embedding Factorization for Compression Using Distilled Nonlinear Neural Decomposition EMNLP Findings

Vasileios Lioutas | Ahmad Rashid | Krtin Kumar | Md. Akmal Haidar | Mehdi Rezagholizadeh |

Latent Code and Text-based Generative Adversarial Networks for Soft-text Generation NAACL

Md. Akmal Haidar | Mehdi Rezagholizadeh | Alan Do Omri | Ahmad Rashid |

Bilingual-GAN: A Step Towards Parallel Text Generation NAACL WS

Ahmad Rashid | Alan Do-Omri | Md. Akmal Haidar | Qun Liu | Mehdi Rezagholizadeh |