# Finding Syntactic Representations in Neural Stacks

arXiv: https://arxiv.org/abs/1906.01594 · HTML: https://mlsanity.com/paper/1906.01594/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Jun 2019.

## Built on by (most cited first, 4 of 4)

- [Transformers Generalize Linearly](https://mlsanity.com/paper/2109.12036/) (2021)
- [Learning Hierarchical Structures with Differentiable Nondeterministic Stacks](https://mlsanity.com/paper/2109.01982/) (2021)
- [Formal Language Theory Meets Modern NLP](https://mlsanity.com/paper/2102.10094/) (2021)
- [Recoding latent sentence representations -- Dynamic gradient-based activation modification in RNNs](https://mlsanity.com/paper/2101.00674/) (2021)

## Abstract (arXiv)

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.