Proceedings of the 2019 ACL Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP
Venue: BlackboxNLP
Type: Workshop
Interpretability
Formal Languages
Syntax
Architectures
Authors
Affiliation
William Merrill
Yale University
Lenny Khazan
Yale University
Noah Amsel
Yale University
Sophie Hao
Yale University
Simon Mendelsohn
Yale University
Robert Frank
Yale University
Published
August 1, 2019
Abstract
Neural network architectures have been augmented with differentiable stacks in order to introduce a bias toward learning hierarchy-sensitive regularities. It has, however, proven difficult to assess the degree to which such a bias is effective, as the operation of the differentiable stack is not always interpretable. In this paper, we attempt to detect the presence of latent representations of hierarchical structure through an exploration of the unsupervised learning of constituency structure. Using a technique due to Shen et al. (2018a,b), we extract syntactic trees from the pushing behavior of stack RNNs trained on language modeling and classification objectives. We find that our models produce parses that reflect natural language syntactic constituencies, demonstrating that stack RNNs do indeed infer linguistically relevant hierarchical structure.