Mehdi Rezagholizadeh

发表

KroneckerBERT: Significant Compression of Pre-trained Language Models Through Kronecker Decomposition and Knowledge Distillation

Marzieh S. Tahaei, A. Ghodsi, V. Nia, 2022, NAACL.

Towards Understanding Label Regularization for Fine-tuning Pre-trained Language Models

P. Poupart, A. Ghodsi, Tianda Li, 2022, ArXiv.

Integer Fine-tuning of Transformer-based Models

Marzieh S. Tahaei, V. Nia, M. Asgharian, 2022, ArXiv.

DyLoRA: Parameter Efficient Tuning of Pre-trained Models using Dynamic Search-Free Low-Rank Adaptation

A. Ghodsi, I. Kobyzev, Mehdi Rezagholizadeh, 2022, ArXiv.

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

Ahmad Rashid, Qun Liu, P. Langlais, 2022, ArXiv.

KronA: Parameter Efficient Tuning with Kronecker Adapter

Marzieh S. Tahaei, J. J. Clark, V. Nia, 2022, ArXiv.

Improving Generalization of Pre-trained Language Models via Stochastic Weight Averaging

A. Ghodsi, P. Langlais, Ahmad Rashid, 2022, EMNLP.

Bilingual-GAN: A Step Towards Parallel Text Generation

Md. Akmal Haidar, Qun Liu, Ahmad Rashid, 2019, Proceedings of the Workshop on Methods for Optimizing and Evaluating Neural Language Generation.

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

Ahmad Rashid, Qun Liu, Xinyu Duan, 2022, EMNLP.

Making a MIRACL: Multilingual Information Retrieval Across a Continuum of Languages

Nandan Thakur, Qun Liu, Xinyu Zhang, 2022, ArXiv.

DyLoRA: Parameter-Efficient Tuning of Pre-trained Models using Dynamic Search-Free Low-Rank Adaptation

A. Ghodsi, I. Kobyzev, Mehdi Rezagholizadeh, 2022, EACL.

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

Ali Ghodsi, Pranav Sharma, Aref Jafari, 2021, EMNLP.

Continuation KD: Improved Knowledge Distillation through the Lens of Continuation Optimization

P. Poupart, A. Ghodsi, I. Kobyzev, 2022, Conference on Empirical Methods in Natural Language Processing.

Compressing Pre-trained Language Models using Progressive Low Rank Decomposition

Omar Mohamed Awad, Marzieh S. Tahaei, Yang Liu, 2021 .

Universal-KD: Attention-based Output-Grounded Intermediate Layer Knowledge Distillation

Ali Ghodsi, Abbas Ghaddar, Md. Akmal Haidar, 2021, EMNLP.

Simple Yet Effective Neural Ranking and Reranking Baselines for Cross-Lingual Information Retrieval

Jimmy J. Lin, Rodrigo Nogueira, Nandan Thakur, 2023, ArXiv.

Pro-KD: Progressive Distillation by Following the Footsteps of the Teacher pdf

Ali Ghodsi, Ali Saheb Pasand, Pranav Sharma, 2021, COLING.

Kronecker Decomposition for GPT Compression pdf

Vahid Partovi Nia, Marzieh S. Tahaei, Marzieh Tahaei, 2021, ACL.

AraMUS: Pushing the Limits of Data and Model Scale for Arabic Natural Language Processing

Xinyu Duan, Zhefeng Wang, Baoxing Huai, 2023, ACL.

Towards Fine-tuning Pre-trained Language Models with Integer Forward and Backward Propagation

Marzieh S. Tahaei, V. Nia, M. Asgharian, 2022, FINDINGS.

CILDA: Contrastive Data Augmentation Using Intermediate Layer Knowledge Distillation

Md. Akmal Haidar, P. Poupart, P. Langlais, 2022, COLING.

Learning Functions on Multiple Sets using Multi-Set Transformers

Kira A. Selby, P. Poupart, Ahmad Rashid, 2022, UAI.

LABO: Towards Learning Optimal Label Regularization via Bi-level Optimization

P. Langlais, Ahmad Rashid, I. Kobyzev, 2023, ACL.

Attribute Controlled Dialogue Prompting

P. Poupart, Ahmad Rashid, I. Kobyzev, 2023, ACL.

Evaluating Embedding APIs for Information Retrieval

Nandan Thakur, Jimmy Lin, Odunayo Ogundepo, 2023, ACL.

Practical Takes on Federated Learning with Pretrained Language Models

Prasanna Parthasarathi, Mehdi Rezagholizadeh, Ankur Agarwal, 2023, FINDINGS.

Bilingual-GAN: A Step Towards Parallel Text Generation pdf

Qun Liu, Mehdi Rezagholizadeh, Md. Akmal Haidar, 2019, Proceedings of the Workshop on Methods for Optimizing and Evaluating Neural Language Generation.

JABER and SABER: Junior and Senior Arabic BERt

Philippe Langlais, Abbas Ghaddar, Duan Xinyu, 2021, 2112.04329.

JABER: Junior Arabic BERt pdf

Philippe Langlais, Abbas Ghaddar, Duan Xinyu, 2021, ArXiv.

A Short Study on Compressing Decoder-Based Language Models pdf

Habib Hajimolahoseini, Ivan Kobyzev, Yang Liu, 2021, ArXiv.

Sorted LLaMA: Unlocking the Potential of Intermediate Layers of Large Language Models for Dynamic Inference Using Sorted Fine-Tuning (SoFT)

Marzieh S. Tahaei, Boxing Chen, P. Kavehzadeh, 2023, 2309.08968.

MIRACL: A Multilingual Retrieval Dataset Covering 18 Diverse Languages

Nandan Thakur, Qun Liu, Odunayo Ogundepo, 2023, Transactions of the Association for Computational Linguistics.

When Chosen Wisely, More Data Is What You Need: A Universal Sample-Efficient Strategy For Data Augmentation

A. Ghodsi, Ehsan Kamalloo, Mehdi Rezagholizadeh, 2022, FINDINGS.

NoMIRACL: Knowing When You Don't Know for Robust Multilingual Retrieval-Augmented Generation

Nandan Thakur, Odunayo Ogundepo, Ehsan Kamalloo, 2023, 2312.11361.

On the utility of enhancing BERT syntactic bias with Token Reordering Pretraining

Prasanna Parthasarathi, Mehdi Rezagholizadeh, Abbas Ghaddar, 2023, CONLL.

Measuring the Knowledge Acquisition-Utilization Gap in Pretrained Language Models

Sarath Chandar, Prasanna Parthasarathi, Mehdi Rezagholizadeh, 2023, EMNLP.

Beyond the Limits: A Survey of Techniques to Extend the Context Length in Large Language Models

A. Eshaghi, Xindi Wang, Mahsa Salmani, 2024, ArXiv.

CHIQ: Contextual History Enhancement for Improving Query Rewriting in Conversational Search

Boxing Chen, Kelong Mao, Mehdi Rezagholizadeh, 2024, 2406.05013.

Towards Practical Tool Usage for Continually Learning LLMs

Sarath Chandar, Prasanna Parthasarathi, Mehdi Rezagholizadeh, 2024, ArXiv.