Chadi Helwe

Chadi Helwe

Postdoctoral Researcher

INRIA, CEDAR Team

Biography

I am a Postdoctoral Researcher at INRIA within the CEDAR team, France, working on bias detection and mitigation in large language models. I completed my Ph.D. in Artificial Intelligence at the Institut Polytechnique de Paris, under the supervision of Prof. Fabian Suchanek and Prof. Chloé Clavel, where I focused on evaluating and improving the reasoning abilities of language models. I hold an MSc in Computer Science from the American University of Beirut and a BSc from Notre Dame University - Louaize. My research spans areas such as Arabic Natural Language Processing (NLP), machine learning for healthcare, and enhancing the reasoning capabilities of language models.

Interests
  • Artificial Intelligence
  • Machine Learning/Deep Learning
  • Natural Language Processing
  • Biomedical Imaging
Education
  • Ph.D. in Artificial Intelligence, 2024

    Institut Polytechnique de Paris

  • MSc in Computer Science, 2017

    American University of Beirut

  • BSc in Computer Science, 2014

    Notre Dame University - Louaize

Teaching Activities

 
 
 
 
 
Teaching Assistant
September 2021 – Present

Courses:

  • Mining of Large Datasets
  • Bases de Données
  • Données du Web
 
 
 
 
 
Teaching Assistant
February 2015 – May 2020

Courses:

  • Artificial Intelligence
  • Introduction to Programming
  • Compiler Construction (graduate course)
  • Machine Learning (graduate course)
 
 
 
 
 
Teaching Assistant
February 2013 – June 2013

Courses:

  • Program Design and Data Abstraction I
  • Program Design and Data Abstraction II

Open Source Projects

LogiTorch

LogiTorch is a PyTorch-based library for logical reasoning on natural language, it consists of:

  • Textual logical reasoning datasets
  • Implementations of different logical reasoning neural architectures
  • A simple and clean API that can be used with PyTorch Lightning
LogiTorch

Selected Publications

Quickly discover relevant content by filtering publications.
(2022). TINA: Textual Inference with Negation Augmentation. Findings of the Association for Computational Linguistics: EMNLP 2022.

PDF

(2022). LogiTorch: A PyTorch-based library for logical reasoning on natural language. Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: System Demonstrations.

PDF

(2021). Reasoning with transformer-based models: Deep learning, but shallow reasoning. 3rd Conference on Automated Knowledge Base Construction (AKBC 2021).

PDF

(2020). A Semi-Supervised BERT Approach for Arabic Named Entity Recognition. Proceedings of the Fifth Arabic Natural Language Processing Workshop (WANLP 2020).

PDF

(2020). A Deep Learning Approach to Detect the Demarcation Line in OCT Images. 24th Annual Conference on Medical Image Understanding and Analysis (MIUA 2020).

(2019). Assessing Arabic Weblog Credibility via Deep Co-learning. Proceedings of the Fourth Arabic Natural Language Processing Workshop (WANLP 2019).

PDF

(2019). Arabic Named Entity Recognition via Deep Co-learning. Artificial Intelligence Review (AI Review 2019).

(2017). CCS Coding of Discharge Diagnoses via Deep Neural Networks. Proceedings of the 2017 International Conference on Digital Health (DH 2017).

(2017). Methodical Evaluation of Arabic Word Embeddings. Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (ACL 2017).

PDF