Avatar

Hassan Sajjad

Associate Professor

Faculty of Computer Science, Dalhousie University, Halifax, Canada

About me

I am a Faculty member in the Faculty of Computer Science and Director of HyperMatrix at Dalhousie University, Halifax, Canada. I am an AI researcher with domain expertise in Natural Language Processing and Safe and Trustworthy AI. Moreover, I am a consultant and a mentor blended with entrepreneurial interests.

Research Interest

NLP, Deep learning, Safe and Trustworthy AI – language generation, interpretability and explainability, generalization and robustness, social and safety alignment, model editing

Recent News

Papers
  • Accepted Papers 2024: 2 papers (NeurIPS), 2 papers (NAACL), 2 papers (EMNLP)
  • Accepted Papers 2023: 3 conference papers (Neurips, ICLR, ACL), 1 Journal (JMLR), 3 demo papers (AAAI, ACL, EACL)
  • Neurips 2023: Evaluating Neuron Interpretation Methods of NLP Models
  • ICLR 2023: Learning Uncertainty for Unknown Domains with Zero-Target-Assumption
  • JMLR 2023: Discovering Salient Neurons in deep NLP models
  • ACL Demo 2023: NeuroX 2.0 Library for Neuron Analysis of Deep NLP Models
  • ACL findings 2023: Impact of Adversarial Training on Robustness and Generalizability of Language Models
Talks
  • Latent Space Exploration for Safe and Trustworthy AI Models. Representation learning for NLP at ACL (Aug. 2024) (Keynote)
  • Latent Space Exploration for Safe and Trustworthy AI Models. MBZUAI, Abu Dhabi (Aug. 2024)
  • Latent Space Exploration for Safe and Trustworthy AI Models. AI@Thomson Reuters (Apr. 2024)
  • Latent Concept based Explanation of Deep Learning Models. MBZUAI, Abu Dhabi (Nov. 2023)
  • Latent Concepts in Transformer Models of NLP. UKP, TU Darmstadt, Germany (Jun. 2023)
  • Knowledge Manifolds in Transformer Models of NLP, National Research Council (NRC), Canada (Apr. 2023)
  • Knowledge Manifolds in Transformer Models of NLP, University of Ottawa, Canada (Apr. 2023)
Service
  • Area chair @ NeurIPS 202324, Area chair @ ARR 2024, Area chair @ EMNLP 2023, Tutorial chair @ EMNLP 2023
Misc
See all previous news here: News

Recent Talks

  • Latent Space Exploration for Safe and Trustworthy AI Models. AI@Thomson Reuters (Apr. 2024)
  • Neuron Interpretation of Deep NLP Models. ITU, Lahore, Pakistan (Dec. 2023)
  • Latent Concept based Explanation of Deep Learning Models. MBZUAI, Abu Dhabi (Nov. 2023)
  • Latent Concepts in Transformer Models of NLP. UKP, TU Darmstadt, Germany (Jun. 2023)
  • Knowledge Manifolds in Transformer Models of NLP, National Research Council (NRC), Canada (Apr. 2023)
  • Knowledge Manifolds in Transformer Models of NLP, University of Ottawa, Canada (Apr. 2023)
  • Analyzing Latent Concepts in Deep Neural Network Models of NLP. STCI Microsoft, India (Jun. 2022)
  • Analyzing Latent Concepts in Deep Neural Network Models of NLP. Data Science Institute, National University of Ireland Galway, (Jun. 2022)
  • Exploiting Redundancy in Pre-trained Models for Efficient Transfer Learning, Machine Learning and Data Analytics Symposium, Qatar (Mar. 2021), Facebook, US (Feb 2021) and National Research Council, Canada (Nov. 2020)
  • Interpreting Deep NLP Models, University of Edinburgh, UK (April 2020)
  • Summarizing Research on Interpreting Machine Translation Models, University of Sheffield, UK (Mar 2020)
  • Efficient Transfer Learning of Pretrained Model, 7th International Conference on Language and Technology, Pakistan (February 2020)
  • Analyzing Individual Neurons in Deep NLP Models at Google, Facebook, Amazon, Salesforce and Bosch, US (April 2019)
  • Hidden Linguistics in Deep NLP Models, Symposium on Natural Language Processing, University of Moratuwa, Sri Lanka (March 2019)
See all previous talks here: Talks

Recent Publications

Quickly discover relevant content by filtering publications.

Evaluating Neuron Interpretation Methods of NLP Models

NeuroX Library for Neuron Analysis of Deep NLP Models

Learning Uncertainty for Unknown Domains with Zero-Target-Assumption

NxPlain: A Web-based Tool for Discovery of Latent Concepts