Episode 36 | Dieuwke Hupkes

Hierarchy and interpretability in neural models of language processing

Papers and Links:

• Homepage
• Google Scholar
• Thesis
• The paradox of the compositionality of natural language: a neural machine translation case study
• Mechanisms for handling nested dependencies in neural-network language models and humans
• Causal Transformers Perform Below Chance on Recursive Nested Constructions, Unlike Humans

Listen: