About Me

I am a Ph.D. student in the Computational Language Understanding (CLU) Lab at the University of Massachusetts Lowell, where I am advised by Professor Hadi Amiri. Previously, I received my BS in Computer Science from KAIST.

My research focuses on curriculum learning and controlled text generation, with an emphasis on linguistic analysis. I develop methods to enhance model training through curriculum learning techniques and investigate the use of linguistic features to analyze datasets and models. My work aims to improve training efficiency and model robustness while enabling precise control over generated text's linguistic properties.

Publications

Preprint

Mohamed Elgaar, Hadi Amiri, P-Masking: Power Law Masking Improves Multi-attribute Controlled Generation, [PDF]

Mohamed Elgaar, Hadi Amiri, Multi-Attribute Linguistic Tuning for Controlled Paraphrase Generation, [PDF]

Hadi Amiri, Nidhi Vakil, Mohamed Elgaar, Jiali Cheng, Mitra Mohtarami, Adrian Wong, Mehrnaz Sadrolashrafi, Leo Anthony G Celi, Analysis of Race, Sex, and Language Proficiency Disparities in Documented Medical Decisions, medRxiv 2024.07.11.24310289 [PDF]

Peer-Reviewed

Mohamed Elgaar, Jiali Cheng, Nidhi Vakil, Hadi Amiri, Leo Anthony Celi, MedDec: A Dataset for Extracting Medical Decisions from Clinical Narratives, Findings of ACL 2024 [PDF] [Code]

Jiali Cheng, Mohamed Elgaar, Nidhi Vakil, Hadi Amiri, CogniVoice: Multimodal and Multilingual Fusion Networks for Mild Cognitive Impairment Assessment from Spontaneous Speech, INTERSPEECH 2024 [PDF] [Code]

Mohamed Elgaar, Hadi Amiri, Ling-CL: Multiview Curriculum Learning using Linguistic Complexity, EMNLP 2023 [PDF] [Code]

Mohamed Elgaar, Hadi Amiri, HuCurl: Human-induced Curriculum Discovery, ACL 2023 [PDF] [Code]

Mohamed Elgaar, Jungbae Park, Sang Wan Lee, Multi-Speaker and Multi-Domain Emotional Voice Conversion Using Factorized Hierarchical Variational Autoencoder, IEEE ICASSP 2020 [PDF] [Demo]

Patents

Mohamed Elgaar, Jungbae Park, Methods for Emotional Voice Conversion, Korean patent (10-2277205)

Awards

KAIST College of Engineering Innovator Award (2020)

Invited Talks

CS Reading Group, Qazvin Islamic Azad University. Understanding NLP Models through Linguistic Curricula. July 9, 2024.

Teaching Assistant

Foundations of Computer Science - UMass Lowell, Fall 2024

Academic Service

Served as a reviewer for the following conferences:

• Association for the Advancement of Artificial Intelligence (AAAI) - 2021, 2022
• International Conference on Machine Learning (ICML) - 2021, 2022
• Conference on Neural Information Processing Systems (NeurIPS) - 2022, 2023, 2024
• Association for Computational Linguistics (ACL) - 2023
• Empirical Methods in Natural Language Processing (EMNLP) - 2023
• ACL Rolling Review (ARR) - Oct'23^★, Dec'23, June'24, Oct'24