Potential Topics

These are some topics that interest me. But I am open to new ideas and topics. In fact, a major portion of your research time will be spent on finding good problems to work on.

1. Representation Learning for language (text embeddings, better architectures, structure induction)
2. Multimodality, Web Agents, Language in Grounded Environments
3. Alignment and Safety (better RLHF)
Retrieval-augmented Generation/Question Answering
5. Compositionality and Reasoning
6. Model-based Linguistics (structure induction)
7. Probing Deep Learning Models (Bias, Interpretability)
8. NLP for Software Engineering (code search, generating comments)
9. Linguistic Representations (universal dependencies, logical Forms, syntax to semantics, CCG, parsing)

Some of these topics can be co-supervised with other faculty at MILA and McGill.