# Learning Latent Trees with Stochastic Perturbations and Differentiable Dynamic Programming

arXiv: https://arxiv.org/abs/1906.09992 · HTML: https://mlsanity.com/paper/1906.09992/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Jun 2019.

## Built on by (most cited first, 7 of 7)

- [SPECTRA: Sparse Structured Text Rationalization](https://mlsanity.com/paper/2109.04552/) (2021)
- [Structured Reordering for Modeling Latent Alignments in Sequence Transduction](https://mlsanity.com/paper/2106.03257/) (2021)
- [Modeling Hierarchical Structures with Continuous Recursive Neural Networks](https://mlsanity.com/paper/2106.06038/) (2021)
- [Conversational Semantic Role Labeling with Predicate-Oriented Latent Graph](https://mlsanity.com/paper/2210.03037/) (2022)
- [Efficient Beam Tree Recursion](https://mlsanity.com/paper/2307.10779/) (2023)
- [Learning with Latent Structures in Natural Language Processing: A Survey](https://mlsanity.com/paper/2201.00490/) (2022)
- [Speaker-Oriented Latent Structures for Dialogue-Based Relation Extraction](https://mlsanity.com/paper/2109.05182/) (2021)

## Abstract (arXiv)

We treat projective dependency trees as latent variables in our probabilistic model and induce them in such a way as to be beneficial for a downstream task, without relying on any direct tree supervision. Our approach relies on Gumbel perturbations and differentiable dynamic programming. Unlike previous approaches to latent tree learning, we stochastically sample global structures and our parser is fully differentiable. We illustrate its effectiveness on sentiment analysis and natural language inference tasks. We also study its properties on a synthetic structure induction task. Ablation studies emphasize the importance of both stochasticity and constraining latent structures to be projective trees.