Despite the tremendous success, existing machine learning models still fall short of human-
like systematic generalization--learning compositional rules from limited data and applying …

Can we teach natural language understanding models to track their beliefs through
intermediate points in text? We propose a representation learning framework called …

Large language models (LLMs) often struggle with complex logical reasoning due to logical
inconsistencies and the inherent difficulty of such reasoning. We use Lean, a theorem …

Extracting structured and grounded fact triples from raw text is a fundamental task in
Information Extraction (IE). Existing IE datasets are typically collected from Wikipedia …

This thesis investigates how natural language understanding and generation with
transformer models can benefit from grounding the models with knowledge representations …

Recently neural network based approaches to knowledge-intensive NLP tasks, such as
question answering, started to rely heavily on the combination of neural retrievers and …