Paul Soulos,Tom McCoy,Tal Linzen,Paul Smolensky
ICLR 2020 1
Artifact development version:
Abstract URL: https://arxiv.org/abs/1910.09113v2
Neural networks are able to perform tasks that rely on compositional structure even though they lack obvious mechanisms for representing this structure. To analyze the internal representations that enable such success, we propose ROLE, a technique that detects whether these representations implicitly encode symbolic structure. ROLE learns to approximate the representations of a target encoder E by learning a symbolic constituent structure and an embedding of that structure into E's representational vector space. The constituents of the approximating symbol structure are defined by structural positions - roles - that can be filled by symbols. We show that when E is constructed to explicitly embed a particular type of structure (string or tree), ROLE successfully extracts the ground-truth roles defining that structure. We then analyze a GRU seq2seq network trained to perform a more complex compositional task (SCAN), where there is no ground truth role scheme available. For this model, ROLE successfully discovers an interpretable symbolic structure that the model implicitly uses to perform the SCAN task, providing a comprehensive account of the representations that drive the behavior of a frequently-used but hard-to-interpret type of model. 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 resulting output is changed in the way predicted by our analysis. Finally, we use ROLE to explore whether popular sentence embedding models are capturing compositional structure and find evidence that they are not; we conclude by suggesting how insights from ROLE can be used to impart new inductive biases to improve the compositional abilities of such models.