# Towards Dynamic Computation Graphs via Sparse Latent Structure

arXiv: https://arxiv.org/abs/1809.00653 · HTML: https://mlsanity.com/paper/1809.00653/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Sep 2018.

## Built on by (most cited first, 2 of 2)

- [To be Closer: Learning to Link up Aspects with Opinions](https://mlsanity.com/paper/2109.08382/) (2021)
- [Learning with Latent Structures in Natural Language Processing: A Survey](https://mlsanity.com/paper/2201.00490/) (2022)

## Abstract (arXiv)

Deep NLP models benefit from underlying structures in the data---e.g., parse trees---typically extracted using off-the-shelf parsers. Recent attempts to jointly learn the latent structure encounter a tradeoff: either make factorization assumptions that limit expressiveness, or sacrifice end-to-end differentiability. Using the recently proposed SparseMAP inference, which retrieves a sparse distribution over latent structures, we propose a novel approach for end-to-end learning of latent structure predictors jointly with a downstream predictor. To the best of our knowledge, our method is the first to enable unrestricted dynamic computation graph construction from the global latent structure, while maintaining differentiability.