# Learning to Perform Role-Filler Binding with Schematic Knowledge

## TL;DR

This paper demonstrates that neural networks with external memory can learn role-filler binding for arbitrary, unseen fillers without explicit supervision, advancing understanding of how models can generalize structural knowledge.

## Contribution

The work shows that external memory networks can perform role-filler binding for unseen fillers without explicit labels, and introduces neural decoding analyses to interpret learned representations.

## Key findings

- Networks with external memory successfully bind unseen fillers to roles.
- Models generalize role-filler binding beyond training correlations.
- Neural decoding provides insights into learned representations.

## Abstract

Through specific experiences, humans learn relationships underlying the structure of events in the world. Schema theory suggests that we organize this information in mental frameworks called "schemata," which represent our knowledge of the structure of the world. Generalizing knowledge of structural relationships to new situations requires role-filler binding, the ability to associate specific "fillers" with abstract "roles." For instance, when we hear the sentence "Alice ordered a tea from Bob," the role-filler bindings "Alice:customer," "tea:drink," and "Bob:barista" allow us to understand and make inferences about the sentence. We can perform these bindings for arbitrary fillers -- we understand this sentence even if we have never heard the names "Alice," "tea," or "Bob" before. In this work, we define a model as capable of performing role-filler binding if it can recall arbitrary fillers corresponding to a specified role, even when these pairings violate correlations seen during training. Previous work found that models can learn this ability when explicitly told what the roles and fillers are, or when given fillers seen during training. We show that networks with external memory can learn these relationships with fillers not seen during training and without explicitly labeled role-filler bindings, and show that analyses inspired by neural decoding can provide a means of understanding what the networks have learned.