Modular Representation Underlies Systematic Generalization in Neural Natural Language Inference Models
Atticus Geiger, Kyle Richardson, Christopher E. Potts · arXiv (Cornell University) · 2020
In adversarial testing, we pose hard generalization tasks in order to gain insights into the solutions found by our models. What properties must a system have in order to succeed at these hard behavioral tasks? We argue that an essential factor is modular internal structure. Our central contribution is a new experimental method called 'interchange interventions', in which systematic manipulations of model-internal states are related to causal effects on their outputs, thereby allowing us to identify modular structure. Our work is grounded empirically in a new challenge Natural Language Inference dataset designed to assess systems on their ability to reason about entailment and negation. We find that a BERT model is strikingly successful at the systematic generalization task we pose using this dataset, and our active manipulations of model-internal vectors help us understand why: despite the densely interconnected nature of the BERT architecture, the learned model embeds modular, general theories of lexical entailment relations.