Discovering the Compositional Structure of Vector Representations with Role Learning Networks

Abstract

How can neural networks perform so well on compositional tasks even though they lack explicit compositional representations? We use a novel analysis technique called ROLE to show that recurrent neural networks perform well on such tasks by converging to solutions which implicitly represent symbolic structure. This method uncovers a symbolic structure which, when properly embedded in vector space, closely approximates the encodings of a standard seq2seq network trained to perform the compositional SCAN task. We verify the causal importance of the discovered symbolic structure by showing that, when we systematically manipulate hidden embeddings based on this symbolic structure, the model's output is changed in the way predicted by our analysis.

References in corpus (6)

• Sequence to Sequence Learning with Neural Networks
• Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
• Language Models are Few-Shot Learners
• Skip-Thought Vectors
• Correlating neural and symbolic representations of language
• RNNs Implicitly Implement Tensor Product Representations

Cited by in corpus (1)

• Compositionality decomposed: how do neural networks generalise?